CN115966739B - Fuel cell parameter identification method and system based on improved Hippocampus optimization algorithm - Google Patents
Fuel cell parameter identification method and system based on improved Hippocampus optimization algorithm Download PDFInfo
- Publication number
- CN115966739B CN115966739B CN202310231558.XA CN202310231558A CN115966739B CN 115966739 B CN115966739 B CN 115966739B CN 202310231558 A CN202310231558 A CN 202310231558A CN 115966739 B CN115966739 B CN 115966739B
- Authority
- CN
- China
- Prior art keywords
- current density
- fuel cell
- hippocampal
- individual
- solid oxide
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 239000000446 fuel Substances 0.000 title claims abstract description 117
- 238000005457 optimization Methods 0.000 title claims abstract description 77
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 73
- 210000001320 hippocampus Anatomy 0.000 title claims abstract description 53
- 238000000034 method Methods 0.000 title claims abstract description 50
- 230000000971 hippocampal effect Effects 0.000 claims abstract description 87
- 239000007787 solid Substances 0.000 claims abstract description 87
- 238000005259 measurement Methods 0.000 claims abstract description 15
- VREFGVBLTWBCJP-UHFFFAOYSA-N alprazolam Chemical compound C12=CC(Cl)=CC=C2N2C(C)=NN=C2CN=C1C1=CC=CC=C1 VREFGVBLTWBCJP-UHFFFAOYSA-N 0.000 claims abstract description 14
- 101000831205 Danio rerio Dynein axonemal assembly factor 11 Proteins 0.000 claims description 50
- 102100024282 Dynein axonemal assembly factor 11 Human genes 0.000 claims description 50
- 241001559542 Hippocampus hippocampus Species 0.000 claims description 50
- 101000831210 Homo sapiens Dynein axonemal assembly factor 11 Proteins 0.000 claims description 50
- 239000013598 vector Substances 0.000 claims description 29
- 230000006870 function Effects 0.000 claims description 17
- 230000009471 action Effects 0.000 claims description 16
- 238000004364 calculation method Methods 0.000 claims description 16
- 230000035772 mutation Effects 0.000 claims description 12
- 230000008569 process Effects 0.000 claims description 11
- 230000005653 Brownian motion process Effects 0.000 claims description 6
- 238000005537 brownian motion Methods 0.000 claims description 6
- 238000010276 construction Methods 0.000 claims description 6
- 238000012804 iterative process Methods 0.000 claims description 5
- 238000009395 breeding Methods 0.000 claims description 4
- 230000001488 breeding effect Effects 0.000 claims description 4
- 241001081178 Cryptocarya Species 0.000 claims description 3
- 230000001174 ascending effect Effects 0.000 claims description 3
- 238000005295 random walk Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 230000006399 behavior Effects 0.000 claims description 2
- 244000062804 prey Species 0.000 claims description 2
- 230000001902 propagating effect Effects 0.000 claims description 2
- 239000000463 material Substances 0.000 claims 1
- 238000004088 simulation Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 3
- 239000003054 catalyst Substances 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000037023 motor activity Effects 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 230000002028 premature Effects 0.000 description 2
- 238000002922 simulated annealing Methods 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 230000000644 propagated effect Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000011273 social behavior Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/30—Hydrogen technology
- Y02E60/50—Fuel cells
Landscapes
- Fuel Cell (AREA)
Abstract
The invention relates to the technical field of fuel cells, in particular to a fuel cell parameter identification method and system based on an improved hippocampal optimization algorithm. Collecting experimental values of the solid oxide fuel cell output voltage at a plurality of moments, and calculating a theoretical value of the solid oxide fuel cell output voltage at each moment; selecting constraint conditions of decision variables such as slope of a Tafil line and the like to construct parameters, and constructing a solid oxide fuel cell optimization model by taking the minimum mean square error of a calculated value of output voltage and an experimental measurement value as an objective function; and taking parameters such as the slope of the Tafil line and the like as variables to be solved, and solving the solid oxide fuel cell optimization model by improving a hippocampus optimization algorithm to obtain optimized parameters and optimized open-circuit voltage. The invention improves the local optimizing capability of the algorithm, helps the algorithm to more quickly locate the accurate position of the local optimal solution, and further improves the accuracy of fuel cell parameter identification.
Description
Technical Field
The invention relates to the technical field of fuel cells, in particular to a fuel cell parameter identification method and system based on an improved hippocampal optimization algorithm.
Background
With the continuous development of renewable energy technology, future worldwide electrical energy consumption will be provided by renewable energy sources. The fuel cell is a device capable of directly converting chemical energy into electrochemical energy, can provide required electric energy for external loads, and has the advantages of good performance, high efficiency, noiseless operation, high power-heat ratio, simple maintenance service, high operating efficiency of partial load, no pollution gas emission and the like in the working process. However, the solid oxide fuel cell is a high temperature fuel cell and the working conditions are relatively closed, which brings certain challenges to the analysis and dynamic control of the internal parameters of the solid oxide fuel cell.
The parameter analysis of the solid oxide fuel cell is complex, and is a nonlinear non-convex problem, and the traditional optimization method such as a linear programming method, a Newton-Lawson method and the like is difficult to obtain accurate solid oxide fuel cell parameters due to serious dependence on gradient information and initialization conditions. In this context, intelligent algorithms provide a more efficient solution to the solution of solid oxide fuel cell parameters, which does not require gradient information or specific initial conditions. If the intelligent algorithm is adopted to optimize the parameters of the solid oxide fuel cell, the cost and the operation time are greatly saved.
Hippocampus optimization algorithms (SHO) use population wisdom to search for optimal solutions in solution space by mimicking common and familiar social behaviors such as movement, predation, and reproduction of the hippocampus. The device has the advantages of simple structure, good development performance and the like, but the defects of low searching efficiency and premature convergence in practical application still need to be improved.
Disclosure of Invention
The invention aims to provide a parameter identification method of a solid oxide fuel cell, which is used for obtaining an optimal solution of the solid oxide fuel cell parameters, so that the theoretical value and the measured value of the output voltage of the solid oxide fuel cell are as close as possible, and the accurate identification of the solid oxide fuel cell parameters is realized, thereby facilitating the further performance prediction and fault analysis of the solid oxide fuel cell.
The technical problems of the invention are mainly solved by the following technical proposal:
a fuel cell parameter identification method based on improved Hippocampus optimization algorithm comprises
Collecting experimental values of the solid oxide fuel cell output voltage at a plurality of moments, and calculating a theoretical value of the solid oxide fuel cell output voltage at each moment;
selecting the slope of a tafel line, anode current density, cathode current density, ion resistance, constant factor, limiting current density and open-circuit voltage as constraint conditions of decision variable construction parameters, and constructing a solid oxide fuel cell optimization model by taking the minimum mean square error of a calculated value and an experimental measurement value of an output voltage as an objective function;
and solving the solid oxide fuel cell optimization model by taking the slope, anode current density, cathode current density, ion resistance, constant factor, limiting current density and open-circuit voltage of the Tafil line as variables to be solved through improving a Hippocampus optimization algorithm to obtain the slope, the optimized anode current density, the optimized cathode current density, the optimized ion resistance, the optimized constant factor, the optimized limiting current density and the optimized open-circuit voltage of the Tafil line.
In the fuel cell parameter identification method based on the improved hippocampal optimization algorithm, the theoretical value calculation formula of the output voltage is as follows:
the measured output voltages of the solid oxide fuel cells at the various times are:
wherein ,for the slope of the Tafil line, +.>For anodic current density>For cathode current density, ">Is an ionic resistance>Is a constant factor, ++>For limiting current density, +.>Is an open circuit voltage>For the total number of cells in the solid oxide fuel cell stack, etc.>For load current density>For outputting voltage +.>Indicate->Measurement output voltage of solid oxide fuel cell at each instant +.>Indicating the number of moments.
In the above fuel cell parameter identification method based on the improved hippocampal optimization algorithm, the objective function is based on the following formula:
wherein ,representing a minimization function +.>For the mean square error of the theoretical value and the experimental measurement value of the output voltage of the solid oxide fuel cell, +.>For the slope of the Tafil line, +.>For anodic current density>For the cathode current density,is an ionic resistance>Is a constant factor, ++>For limiting current density, +.>Is an open circuit voltage.
In the above-described fuel cell parameter identification method based on the improved hippocampal optimization algorithm,the calculation formula is as follows:
wherein :indicate->Theoretical value of solid oxide fuel cell output voltage at each instant +.>Indicate->Experimental measurement output voltage of solid oxide fuel cell at each instant +.>Indicating the number of moments.
In the fuel cell parameter identification method based on the improved hippocampal optimization algorithm, the constraint conditions of the parameters are as follows:
wherein ,=0/>is the lower limit of the open circuit voltage, +.>=1.2/>Is the upper limit of the open circuit voltage, +.>=0/>For the lower limit of the tafel-line slope, < >>=1/>Is the upper limit of the slope of the tafel line, < >>=0/>As a lower limit of the current density of the anode,=100/>is the upper limit of the anode current density, +.>=0/>Is the lower limit of the cathode current density, +.>=100Is the upper limit of the cathode current density, +.>=0/>Is the lower limit of the constant factor, +.>=1/>Is the upper limit of the constant factor,=0/>is the lower limit of the limiting current density, +.>=10000/>Is the upper limit of the limiting current density, +.>=0Is the lower limit of ionic resistance, +.>=1/>Is the upper limit of ionic resistance.
The specific process for solving the improved Hippocampus optimization algorithm based on the fuel cell parameter identification method based on the improved Hippocampus optimization algorithm is as follows:
step 3.1, initializing a hippocampal optimization algorithm, wherein the specific process is as follows:
setting search space of sea horse according to constraint condition of parameterStoring the lower limits of the 7 parameters to be determined in a dimension-by-dimension manner +.>In which the upper limits of the 7 parameters to be determined are stored in dimension by dimension +.>In (I)>For the lower limit of the hippocampal search space, +.>An upper limit for the hippocampal search space;
setting the quantity of Hippocampus in the population asThe maximum iteration number is->Action judging factor->Predation judgment factor->Number of reproducing individuals->The method comprises the steps of carrying out a first treatment on the surface of the Randomly generating a hippocampal population in a hippocampal activity interval, and setting the current iteration number +.>;
Step 3.2, the sea horse searches for hunting objects in two movement behaviors including spiral movement of the sea horse along with vortexes in the sea and Brownian movement of the sea horse along with sea waves,
step 3.3, selecting different routes for preying on prey objects according to Chebyshev distance between the sea horse and the optimal individual, wherein the specific steps are as follows:
calculating chebyshev distances between the remaining Hippocampus individuals and elite individualsJudging whether the distance satisfies +.>If so, the hippocampal individual surrounds the prey according to the formula; if not, the sea horse preys prey, wherein the chebyshev distance calculation formula is as follows:
wherein ,is->Iterative->Chebyshev distance seen by the individual from the optimal individual,>first->Iterative->The location of individual hippocampus, the +.>First->Iterating the position of the optimal sea horse individual;
step 3.4, performing reproduction and mutation operations on the sea horse individuals, wherein the steps are as follows:
performing fitness sequencing on current hippocampal individuals according to an objective function in the solid oxide fuel cell optimization model, performing role allocation on the current hippocampal population, and then propagating to generate offspring hippocampal individuals;
role assignment is specifically defined before fitness rankingIs the parent Hippocampus ++>After definition of fitness row->Is mother generation Hippocampus +.>The formula is as follows:
wherein ,for the parent hippocampal population, cryptocarya>For parent sea horse population, ->Indicate->Hippocampus population in ascending order of fitness for multiple iterations,/->For the number of Hippocampus populations, < >>For interval->Random number between->Indicate->The>Individual offspring hippocampal individuals, < >>Indicate->The>The individual male parent, the individual Hippocampus,indicate->The>Individuals with mother-generation hippocampus;
after the breeding process is finished, the fitness of the hippocampal population is recalculated, and the hunting of the natural enemies is simulated by carrying out position mutation on individuals with better fitness based on a variable-scale mutation strategy, wherein the variable-scale mutation strategy has the following update formula:
wherein ,is->Updated +.>Individual hippocampal individuals,/->For the maximum number of iterations to be performed,to meet mathematical expectations->Variance is->Is a normal distribution of random numbers, wherein mathematical expectation +.>Is equal to zero, variance->Initial set to 1, then every time the history optimal solution changes, let +.>,
Step 3.5: repeating the steps 3.2-3.4 untilIs greater than->And outputting an optimized open-circuit voltage, an optimized tafel line slope, an optimized anode current density, an optimized cathode current density, an optimized constant factor, an optimized limiting current density and an optimized ion resistance.
In the above fuel cell parameter identification method based on the improved hippocampal optimization algorithm, in step 3.1, the definition of the initialized hippocampal population is as follows:
wherein ,indicate->The->Individual hippocampal individuals,/->Indicate->The->Open circuit voltage of individual solution vector, +.>Indicate->The->The tafel-line slope of the individual solution vectors,indicate->The->Anodic current density of individual solution vector, +.>Indicate->The->Cathode current density of individual solution vector, +.>Indicate->The->Constant factor of individual solution vector, +.>Indicate->The->Poles of individual solution vectorsCurrent limiting density->Indicate->The->Ion resistance of individual solution vectors, +.>Indicate->The->No. H of individual Hippocampus>Vector of dimensions>For the dimension of the solution, <' > for>Indicating +.>Lower bound of dimension solution vector parameters +.>Indicating +.>Upper limit of vector parameters of dimension solution, action judgment factor +.>And predatory judgment factor->All are interval +.>Constant of the same.
In the above fuel cell parameter identification method based on improved hippocampal optimization algorithm, in step 3.2, the fitness of all hippocampal individuals in the population is calculated according to the objective function of the solid oxide fuel cell optimization model, and the hippocampal individuals are ranked according to the fitness and the first is selectedElite individuals in the course of a second iteration +.>;
Setting an action factor for each individual HippocampusAnd judging action factor->Whether or not to meet->If the sea wave is satisfied, the current sea horse individual moves in a novel spiral way along with the vortex in the sea, if the sea wave is not satisfied, the current sea horse individual moves in a Brownian way along with the sea wave,
the updated formula of the novel spiral motion of the sea horse individual along with the vortex in the sea is as follows:
parameters (parameters)For the first shape adjustment factor, parameter +.>For the second form factor, parameter +.>For the third shape adjustment factor, the specific calculation formulas are as follows:
the specific update formula of the Brownian motion of the sea horse individual along with sea waves is as follows:
wherein ,is->Updated +.>Individual hippocampal individuals,/->Is->The +.f. before updating in the iterative process>Individual hippocampal individuals,/->To obey mathematical expectations +.>Variance is->Is used for the scaling factor of the gaussian distribution,is->Optimal individual in the course of the second iteration, +.>To round-down function->For the step length adjustment factor, forRandom number between->The iteration times; />Is->Updated +.>The individual sea horse,is->The +.f. before updating in the iterative process>Individual hippocampal individuals,/->For interval->Random number between->Is a constant coefficient>For the Brownian motion random walk coefficient following normal distribution, +.>Is->Optimal individuals after spiral movement in the iterations.
In the fuel cell parameter identification method based on the improved hippocampal optimization algorithm, the position update formula of the hippocampal individual surrounding the hunting object is specifically as follows:
the update formula of the prey position of the sea horse is specifically as follows:
wherein ,for maximum number of iterations +.>For the number of iterations->Is->Elite individuals in the course of a second iteration, +.>For interval->Random number between->Is the number of iterations.
A fuel cell parameter identification system based on improved Hippocampus optimization algorithm comprises
A first module: configured to collect experimental values of solid oxide fuel cell output voltages at a plurality of times, and calculate theoretical values of the solid oxide fuel cell output voltages at each time;
a second module: the solid oxide fuel cell optimization model is configured to select the slope of the tafel line, the anode current density, the cathode current density, the ion resistance, the constant factor, the limiting current density and the open-circuit voltage as constraint conditions of decision variable construction parameters, and construct the solid oxide fuel cell optimization model by taking the minimum mean square error of the calculated value and the experimental measurement value of the output voltage as an objective function;
and a third module: the method is configured to take the slope, anode current density, cathode current density, ion resistance, constant factor, limiting current density and open-circuit voltage of the Tariff line as variables to be solved, and solve a solid oxide fuel cell optimization model by improving a Hippocampus optimization algorithm to obtain the slope, the optimized anode current density, the optimized cathode current density, the optimized ion resistance, the optimized constant factor, the optimized limiting current density and the optimized open-circuit voltage of the Tariff line.
Therefore, the invention has the following advantages:
(1) The novel Archimedes spiral is adopted to replace a spiral formula in the original algorithm to update the sea horse population, so that the action route of the sea horse is enriched, the spatial distribution of the sea horse is optimized, and the global optimizing capability of the algorithm is improved.
(2) The predation mode is judged according to the Chebyshev distance between the sea horse and the optimal individual, and an adaptive position updating strategy is adopted to improve the updating formula of predation and surrounding of prey, so that the local optimizing capability of the algorithm is improved, the algorithm is helped to locate the accurate position of the local optimal solution more quickly, and the accuracy of fuel cell parameter identification is improved.
(3) On the basis of the original algorithm, a variable-scale variation strategy is introduced to simulate the hunting of natural enemies of the sea horse, so that the survival characteristic of the sea horse is better matched, the algorithm can jump out of a local optimal solution faster during optimizing, and premature convergence of the algorithm due to the search of the local optimal solution is avoided.
(4) The sea horse optimization algorithm is improved so that the sea horse optimization algorithm can adapt to a more complex operation model.
Drawings
FIG. 1 is an overall flow chart of a fuel cell parameter identification method based on an improved hippocampal optimization algorithm of the present invention.
FIG. 2 is a flow chart of a fuel cell parameter identification method based on an improved hippocampal optimization algorithm.
Fig. 3 is a graph of theoretical output voltage-current versus measured output voltage-current for a solid oxide fuel cell of the present invention (where the graph represents calculated data and the circle represents measured data).
Fig. 4 is a graph of theoretical output power versus current versus measured for a solid oxide fuel cell of the present invention.
FIG. 5 is a graph of improved hippocampal optimization algorithm (New-SHO), particle Swarm Optimization (PSO), simulated annealing algorithm (SA), and hippocampal optimization algorithm (SHO) versus optimization model employed in simulation experiments of the present invention.
Detailed Description
The technical scheme of the invention is further specifically described below through examples and with reference to the accompanying drawings.
Examples:
the present invention will be further described in detail with reference to the following detailed description and the accompanying drawings.
A fuel cell parameter identification method based on an improved hippocampal optimization algorithm as shown in fig. 1, the method comprising the following steps:
step 1: by analyzing the working principle and the structural characteristics of the solid oxide fuel cell, a mathematical model of the solid oxide fuel cell is established, experimental values of the output voltage of the solid oxide fuel cell at a plurality of moments are collected, and theoretical values of the output voltage of the solid oxide fuel cell at each moment are calculated.
The anode reaction equation of the solid oxide fuel cell in step 1 is as follows:
the cathode reaction equation of the solid oxide fuel cell in step 1 is as follows:
the total chemical reaction equation of the solid oxide fuel cell described in step 1 is as follows:
wherein :under the action of a catalyst, the catalyst is decomposed into protons and electrons; />Combines with electrons and protons under the action of a catalyst to produce water oxygen. />Proton(s)>Is an electron.
The theoretical value calculation formula for calculating the output voltage of the solid oxide fuel cell at each moment in step 1 is as follows:
wherein :indicate->Output voltage of solid oxide fuel cell at each instant, +.>For the number of units in the solid oxide fuel cell stack, for example>Indicate->Open circuit voltage of solid oxide fuel cell at each instant, +.>Indicate->The activation voltage drop of the solid oxide fuel cell at a single instant,/->Indicate->Ohmic drop of solid oxide fuel cell at various moments,/->Indicate->Concentration drop of solid oxide fuel cell at each moment,/->=600 denotes the number of times.
The specific calculation formula after the theoretical value of the output voltage of the solid oxide fuel cell at each moment is brought into each voltage calculation formula in the step 1 is as follows:
fixing at multiple moments as described in step 1The measured output voltage of a bulk oxide fuel cell is defined as:
wherein ,for the slope of the Tafil line, +.>For anodic current density>For cathode current density, ">Is an ionic resistance>Is a constant factor, ++>For limiting current density, +.>Is an open circuit voltage>For the total number of cells in the solid oxide fuel cell stack, etc.>For load current density>For outputting voltage +.>Indicate->Measurement output voltage of solid oxide fuel cell at each instant +.>Indicating the number of moments.
Step 2: and constructing an output voltage optimization target of the solid oxide fuel cell, and selecting the slope of a tafel line, the anode current density, the cathode current density, the ion resistance, the constant factor, the limiting current density and the open-circuit voltage as constraint conditions of decision variable construction parameters. And constructing a solid oxide fuel cell optimization model by taking the minimum mean square error of the calculated value of the output voltage and the experimental measurement value as an objective function.
The solid oxide fuel cell output voltage optimization target is constructed in the step 2, and the method specifically comprises the following steps:
the calculation formula is as follows:
wherein ,representing a minimization function +.>For the mean square error of the theoretical value and the experimental measurement value of the output voltage of the solid oxide fuel cell, +.>For the slope of the Tafil line, +.>For anodic current density>Is a cathodeThe current density is such that,is an ionic resistance>Is a constant factor, ++>For limiting current density, +.>Is an open circuit voltage.
The constraint conditions of the parameters in the step 2 are specifically as follows:
wherein ,=0/>is the lower limit of the open circuit voltage, +.>=1.2/>Is the upper limit of the open circuit voltage, +.>=0/>For the lower limit of the tafel-line slope, < >>=1/>Is the upper limit of the slope of the tafel line, < >>=0/>Is the lower limit of the anode current density, +.>=100/>Is the upper limit of the anode current density, +.>=0/>Is the lower limit of the cathode current density, +.>=100/>Is the upper limit of the cathode current density, +.>=0/>Is the lower limit of the constant factor, +.>=1/>Is the upper limit of the constant factor, +.>=0Is the lower limit of the limiting current density, +.>=10000/>Is the upper limit of the limiting current density, +.>=0/>Is the lower limit of ionic resistance, +.>=1/>Is the upper limit of ionic resistance.
Step 3: and combining constraint conditions of an optimization target and parameters of the output voltage of the solid oxide fuel cell, taking the slope, the anode current density, the cathode current density, the ionic resistance, the constant factor, the limiting current density and the open-circuit voltage of the Tafil line as variables to be solved, and solving by improving a Hippocampus optimization algorithm to obtain the slope, the optimized anode current density, the optimized cathode current density, the optimized ionic resistance, the optimized constant factor, the optimized limiting current density and the optimized open-circuit voltage of the Tafil line.
As shown in fig. 2, the solution by using the modified hippocampal optimization algorithm is described in step 3, and the specific procedure is as follows:
step 3.1: the sea horse optimization algorithm is initialized, and the specific process is as follows:
setting search space of sea horse according to constraint condition of parameterThe method comprises the steps of carrying out a first treatment on the surface of the The lower limit of the 7 parameters to be determined is stored in dimension by dimension +.>In which the upper limits of the 7 parameters to be determined are stored in dimension by dimension +.>In (a) and (b); the method comprises the following steps: />
Is the lower limit of the open circuit voltage, +.>For the lower limit of the tafel-line slope, < >>Is the lower limit of the anode current density, +.>Is the lower limit of the cathode current density, +.>Is the lower limit of the constant factor, +.>Is the lower limit of the limiting current density, +.>Is the lower limit of ionic resistance; />Is the upper limit of the open circuit voltage, +.>Is the upper limit of the slope of the tafel line, < >>Is the upper limit of the anode current density, +.>Is the upper limit of the cathode current density, +.>Is the upper limit of the constant factor, +.>Is the upper limit of the limiting current density, +.>Is the upper limit of ionic resistance.
Setting the quantity of Hippocampus in the population asThe maximum iteration number is->Action judging factor->Predation judgment factor->Number of reproducing individuals->;
Wherein: action judgment factorAnd predatory judgment factor->All are interval +.>Constant of the same.
Randomly generating a hippocampal population in a hippocampal activity interval, and setting the current iteration times;
Wherein the initialized hippocampal population is defined as follows:
wherein ,indicate->The->Individual hippocampal individuals,/->Indicate->The->Open circuit voltage of individual solution vector, +.>Indicate->The->The tafel-line slope of the individual solution vectors,indicate->The->Anodic current density of individual solution vector, +.>Indicate->In the second iteration processCathode current density of individual solution vector, +.>Indicate->The->Constant factor of individual solution vector, +.>Indicate->The->Limiting current density of individual solution vector, +.>Indicate->The->Ion resistance of individual solution vectors, +.>Indicate->The->No. H of individual Hippocampus>Vector of dimensions>For the dimension of the solution, <' > for>Indicating +.>Lower bound of dimension solution vector parameters +.>Indicating +.>Upper limit of vector parameters of dimension solution, action judgment factor +.>And predatory judgment factor->All are interval +.>Constant of the same.
Step 3.2: the hippocampus searches for prey in two motor activities; the two motor activities include spiral movement of the hippocampus with the vortexes in the sea and brownian movement of the hippocampus with the waves. The method comprises the following steps:
calculating the fitness of all the sea horse individuals in the population according to the objective function of the solid oxide fuel cell optimization model in the step 2, sequencing the sea horse individuals according to the fitness, and selecting the first sea horse individualElite individuals in the course of a second iteration +.>。
Setting an action factor for each individual HippocampusAnd judging action factor->Whether or not to meet->If the sea wave is satisfied, the current sea horse individual moves in a novel spiral mode along with the vortex in the sea, and if the sea wave is not satisfied, the current sea horse individual moves in a Brownian mode along with the sea wave.
The updated formula of the novel spiral motion of the sea horse individual along with the vortex in the sea in the step 3.2 is as follows:
wherein :/>Is->Updated +.>Individual hippocampal individuals,/->To obey mathematical expectations +.>Variance is->Is a scaling factor of the gaussian distribution, +.>Is->Optimal individual in the iterative process, parameter ∈ ->The specific calculation formula of the shape adjustment factor is as follows: />
The specific updating formula of the brownian motion of the sea horse individuals along with sea waves in the step 3.2 is as follows:
wherein :is->Updated +.>Individual hippocampal individuals,/->For interval->Random number between->Is a constant coefficient>To follow the normal distribution of the Brownian motion random walk coefficient.
Step 3.3: the hippocampus selects different routes to predate the prey according to its chebyshev distance from the optimal individual. The method comprises the following steps:
calculating the cuts between the other Hippocampus individuals and elite individualsDistance from snowJudging whether the distance is satisfiedIf so, the hippocampal individual surrounds the prey according to the formula; if not, the hippocampus predates the prey. Wherein the chebyshev distance calculation formula is as follows:
Step 3.3, the position update formula of the hippocampal individual surrounding the prey is specifically as follows:
The updated formula of the position of the prey of the sea horse individual in the step 3.3 is specifically as follows:
Step 3.4: the sea horse individuals perform breeding and mutation operations, specifically as follows:
step 3.4, the specific process of the propagation process of the Hippocampus individuals is that the current Hippocampus individuals are adaptively ordered according to the objective function in the solid oxide fuel cell optimization model in the step 2, the role of the current Hippocampus population is allocated, and then the offspring Hippocampus individuals are propagated;
role assignment is specifically defined before fitness rankingIs the parent Hippocampus ++>After definition of fitness row->Is mother generation Hippocampus +.>The formula is as follows: />
wherein :for the parent hippocampal population, cryptocarya>For parent sea horse population, ->Indicate->Hippocampus population in ascending order of fitness for multiple iterations,/->Is the sea horse population quantity.
Step 3.4 the firstThe calculation formula of individual offspring hippocampal individuals is as follows:
wherein :for interval->Random number between->Indicate->The>Individual offspring hippocampal individuals, < >>Indicate->The>Individual male hippocampal individuals, < >>Indicate->The>Personal motherIndividuals with Hippocampus.
And (3) after the breeding process is finished, recalculating the fitness of the hippocampal population, introducing a variable-scale mutation strategy, and carrying out position mutation on individuals with better fitness to simulate natural enemies to kill.
The variable scale mutation strategy updating formula in the step 3.4 is as follows:
wherein :is->Updated +.>Individual hippocampal individuals,/->For the maximum number of iterations to be performed,to meet mathematical expectations->Variance is->Is a normal distribution of random numbers, wherein mathematical expectation +.>Is equal to zero, variance->Initial set to 1, then every time the history optimal solution changes, let +.>。
And 3, step 3.5: repeating the steps 3.2-3.4 untilIs greater than->And outputting an optimized open-circuit voltage, an optimized tafel line slope, an optimized anode current density, an optimized cathode current density, an optimized constant factor, an optimized limiting current density and an optimized ion resistance.
The solid oxide fuel cell parameter identification method of the invention is analyzed by a simulation experiment.
Solid oxide fuel cell in simulation experiment at 1073Carrying in relevant parameters, solving the solid oxide fuel cell model by adopting a simulated annealing algorithm (SA), a particle swarm algorithm (PSO), a hippocampal optimization algorithm (SHO) and a modified hippocampal optimization algorithm (New-SHO), wherein the optimal parameters and RMSE solved by each algorithm are shown in table 1:
table 1: results of each algorithm on solid oxide fuel cell model parameters
As can be seen from table 1: compared with other algorithms, the improved hippocampal optimization algorithm obtains the minimum value of RMSE, and compared with the improved hippocampal optimization algorithm, the improved hippocampal optimization algorithm has greatly optimized RMSE. The result shows that the New-SHO algorithm has better optimizing effect and higher robustness, and the improved Hippocampus optimization algorithm has more remarkable advantages for optimizing the parameters of the solid oxide fuel cell compared with other algorithms.
From fig. 3 and fig. 4, it can be known that the simulation result of the parameter of the solid oxide fuel cell improved by the hippocampal optimization algorithm is very close to the experimental result, which indicates that the New-SHO algorithm has better optimizing capability, the simulation curve is smoother and basically has no fluctuation, and the superiority of the New-SHO algorithm is further verified.
As can be seen from fig. 5, the improved hippocampal optimization algorithm (New-SHO) cloud has stronger capability than other algorithms, so that the global optimizing and local optimizing capabilities of the original algorithm are effectively improved, the solving efficiency of the algorithm is improved, and the identification parameters of the better solid oxide fuel cell are obtained.
The embodiment also provides a fuel cell parameter identification system based on the improved Hippocampus optimization algorithm, which comprises
A first module: configured to collect experimental values of solid oxide fuel cell output voltages at a plurality of times, and calculate theoretical values of the solid oxide fuel cell output voltages at each time;
a second module: the solid oxide fuel cell optimization model is configured to select the slope of the tafel line, the anode current density, the cathode current density, the ion resistance, the constant factor, the limiting current density and the open-circuit voltage as constraint conditions of decision variable construction parameters, and construct the solid oxide fuel cell optimization model by taking the minimum mean square error of the calculated value and the experimental measurement value of the output voltage as an objective function;
and a third module: the method is configured to take the slope, anode current density, cathode current density, ion resistance, constant factor, limiting current density and open-circuit voltage of the Tariff line as variables to be solved, and solve a solid oxide fuel cell optimization model by improving a Hippocampus optimization algorithm to obtain the slope, the optimized anode current density, the optimized cathode current density, the optimized ion resistance, the optimized constant factor, the optimized limiting current density and the optimized open-circuit voltage of the Tariff line.
The specific embodiments described herein are offered by way of example only to illustrate the spirit of the invention. Those skilled in the art may make various modifications or additions to the described embodiments or substitutions thereof without departing from the spirit of the invention or exceeding the scope of the invention as defined in the accompanying claims.
Claims (5)
1. A fuel cell parameter identification method based on improved Hippocampus optimization algorithm is characterized by comprising the following steps of
Collecting experimental values of the solid oxide fuel cell output voltage at a plurality of moments, and calculating a theoretical value of the solid oxide fuel cell output voltage at each moment;
selecting the slope of a tafel line, anode current density, cathode current density, ion resistance, constant factor, limiting current density and open-circuit voltage as constraint conditions of decision variable construction parameters, and constructing a solid oxide fuel cell optimization model by taking the minimum mean square error of a calculated value and an experimental measurement value of an output voltage as an objective function;
the slope of the Tafil line, the anode current density, the cathode current density, the ion resistance, the constant factor, the limiting current density and the open-circuit voltage are used as variables to be solved, and the solid oxide fuel cell optimization model is solved through an improved hippocampus optimization algorithm, so that the slope of the optimized Tafil line, the optimized anode current density, the optimized cathode current density, the optimized ion resistance, the optimized constant factor, the optimized limiting current density and the optimized open-circuit voltage are obtained;
the theoretical value of the output voltage is calculated as follows:
the measured output voltages of the solid oxide fuel cells at the various times are:
wherein ,for the slope of the Tafil line, +.>For anodic current density>For cathode current density, ">In the form of an ionic resistance,is a constant factor, ++>For limiting current density, +.>Is an open circuit voltage>For the total number of cells in the solid oxide fuel cell stack, etc.>For load current density>For outputting voltage +.>Indicate->Measurement output voltage of solid oxide fuel cell at each instant +.>Indicating the number of moments;
wherein the objective function is based on the following formula:
wherein ,representing a minimization function +.>For the mean square error of the theoretical value and the experimental measurement value of the output voltage of the solid oxide fuel cell, +.>For the slope of the Tafil line, +.>For anodic current density>For cathode current density, ">Is an ionic resistance>Is a constant factor, ++>For limiting current density, +.>Is an open circuit voltage;
wherein :indicate->Theoretical value of solid oxide fuel cell output voltage at each instant +.>Indicate->Experimental measurement output voltage of solid oxide fuel cell at each instant +.>Indicating the number of moments;
the constraint conditions of the parameters are specifically as follows:
wherein ,=0/>is the lower limit of the open circuit voltage, +.>=1.2/>Is the upper limit of the open circuit voltage, +.>=0/>For the lower limit of the tafel-line slope, < >>=1/>Is the upper limit of the slope of the tafel line, < >>=0/>Is the lower limit of the anode current density, +.>=100Is the upper limit of the anode current density, +.>=0/>Is the lower limit of the cathode current density, +.>=100/>Is the upper limit of the cathode current density, +.>=0/>Is the lower limit of the constant factor, +.>=1/>Is the upper limit of the constant factor, +.>=0Is the lower limit of the limiting current density, +.>=10000/>Is the upper limit of the limiting current density, +.>=0Is the lower limit of ionic resistance, +.>=1/>Is the upper limit of ionic resistance;
the specific process for solving by improving the hippocampal optimization algorithm is as follows:
step 3.1, initializing a hippocampal optimization algorithm, wherein the specific process is as follows:
setting search space of sea horse according to constraint condition of parameterStoring the lower limit of the 7 parameters to be determined into the memory in a dimension-by-dimension mannerIn which the upper limits of the 7 parameters to be determined are stored in dimension by dimension +.>In (I)>For the lower limit of the hippocampal search space, +.>An upper limit for the hippocampal search space;
setting the quantity of Hippocampus in the population asThe maximum iteration number is->Action judging factor->Predation judgment factor->Number of reproducing individuals->The method comprises the steps of carrying out a first treatment on the surface of the Randomly generating a hippocampal population in a hippocampal activity interval, and setting the current iteration number +.>;
Step 3.2, the sea horse searches for hunting objects in two movement behaviors including spiral movement of the sea horse along with vortexes in the sea and Brownian movement of the sea horse along with sea waves,
step 3.3, selecting different routes for preying on prey objects according to Chebyshev distance between the sea horse and the optimal individual, wherein the specific steps are as follows:
calculating chebyshev distances between the remaining Hippocampus individuals and elite individualsJudgingWhether or not the distance is satisfied->If so, the hippocampal individual surrounds the prey according to the formula; if not, the sea horse preys prey, wherein the chebyshev distance calculation formula is as follows:
wherein ,is->Iterative->Chebyshev distance seen by the individual from the optimal individual,>first->Iterative->The location of individual hippocampus, the +.>First->Iterating the position of the optimal sea horse individual;
step 3.4, performing reproduction and mutation operations on the sea horse individuals, wherein the steps are as follows:
performing fitness sequencing on current hippocampal individuals according to an objective function in the solid oxide fuel cell optimization model, performing role allocation on the current hippocampal population, and then propagating to generate offspring hippocampal individuals;
role assignment is specifically defined before fitness rankingIs the parent Hippocampus ++>After defining fitness measuresIs mother generation Hippocampus +.>The formula is as follows:
wherein ,for the parent hippocampal population, cryptocarya>For parent sea horse population, ->Indicate->Hippocampus population in ascending order of fitness for multiple iterations,/->For the number of Hippocampus populations, < >>For interval->Random number between->Indicate->The>Individual offspring hippocampal individuals, < >>Indicate->The>Individual male hippocampal individuals, < >>Indicate->The>Individuals with mother-generation hippocampus;
after the breeding process is finished, the fitness of the hippocampal population is recalculated, and the hunting of the natural enemies is simulated by position mutation on individuals with better fitness based on a variable-scale mutation strategy, wherein the variable-scale mutation strategy has the following update formula:
wherein ,is->Updated +.>Individual hippocampal individuals,/->For maximum number of iterations +.>To meet mathematical expectations->Variance is->Is a normal distribution of random numbers, wherein mathematical expectation +.>Is equal to zero, variance->Initial set to 1, then every time the history optimal solution changes, let +.>,
Step 3.5: repeating the steps 3.2-3.4 untilIs greater than->And outputting an optimized open-circuit voltage, an optimized tafel line slope, an optimized anode current density, an optimized cathode current density, an optimized constant factor, an optimized limiting current density and an optimized ion resistance.
2. The method for identifying parameters of a fuel cell based on an improved hippocampal optimization algorithm according to claim 1, wherein in step 3.1, the definition of the initialized hippocampal population is as follows:
wherein , indicate->The->Individual hippocampal individuals,/->Indicate->The->Open circuit voltage of individual solution vector, +.>Indicate->The->The tafel-line slope of individual solution vectors,/>Indicate->The->Anodic current density of individual solution vector, +.>Indicate->The->Cathode current density of individual solution vector, +.>Indicate->The->Constant factor of individual solution vector, +.>Indicate->The->Limiting current density of individual solution vector, +.>Indicate->The->Ion resistance of individual solution vectors, +.>Indicate->The->No. H of individual Hippocampus>Vector of dimensions>For the dimension of the solution, <' > for>Indicating +.>Lower bound of dimension solution vector parameters +.>Indicating +.>Upper limit of vector parameters of dimension solution, action judgment factor +.>And predatory judgment factor->All are interval +.>Constant of the same.
3. The method for identifying parameters of fuel cell based on improved hippocampal optimization algorithm as recited in claim 1, wherein in step 3.2, the fitness of all the hippocampal individuals in the population is calculated according to the objective function of the solid oxide fuel cell optimization model, and the hippocampal individuals are ranked according to the fitness and the first is selectedElite individuals in the course of a second iteration +.>;
Setting an action factor for each individual HippocampusAnd judging action factor->Whether or not to meet->If the sea wave is satisfied, the current sea horse individual moves in a novel spiral way along with the vortex in the sea, if the sea wave is not satisfied, the current sea horse individual moves in a Brownian way along with the sea wave,
the updated formula of the novel spiral motion of the sea horse individual along with the vortex in the sea is as follows:
parameters (parameters)For the first shape adjustment factor, parameter +.>For the second form factor, parameter +.>For the third shape adjustment factor, the specific calculation formulas are as follows:
the specific update formula of the Brownian motion of the sea horse individual along with sea waves is as follows:
wherein ,is->Updated +.>Individual hippocampal individuals,/->Is->The +.f. before updating in the iterative process>Individual hippocampal individuals,/->To obey mathematical expectations +.>Variance is->Is a scaling factor of the gaussian distribution, +.>Is->Optimal individual in the course of the second iteration, +.>To round-down function->For step size adjustment factor +.>Random number between->The iteration times; />Is->Updated +.>Individual hippocampal individuals,/->Is->The +.f. before updating in the iterative process>Individual hippocampal individuals,/->For interval->Random number between->Is a constant coefficient of the number of the pieces of the material,for the Brownian motion random walk coefficient following normal distribution, +.>Is->Optimal individuals after spiral movement in the iterations.
4. The method for identifying parameters of a fuel cell based on an improved hippocampal optimization algorithm according to claim 1, wherein the location update formula of the surrounding prey of the hippocampal individual is specifically as follows:
the update formula of the prey position of the sea horse is specifically as follows:
5. A system adapted for use in the improved hippocampal optimization algorithm based fuel cell parameter identification method of claim 1, comprising
A first module: configured to collect experimental values of solid oxide fuel cell output voltages at a plurality of times, and calculate theoretical values of the solid oxide fuel cell output voltages at each time;
a second module: the solid oxide fuel cell optimization model is configured to select the slope of the tafel line, the anode current density, the cathode current density, the ion resistance, the constant factor, the limiting current density and the open-circuit voltage as constraint conditions of decision variable construction parameters, and construct the solid oxide fuel cell optimization model by taking the minimum mean square error of the calculated value and the experimental measurement value of the output voltage as an objective function;
and a third module: the method is configured to take the slope, anode current density, cathode current density, ion resistance, constant factor, limiting current density and open-circuit voltage of the Tariff line as variables to be solved, and solve a solid oxide fuel cell optimization model by improving a Hippocampus optimization algorithm to obtain the slope, the optimized anode current density, the optimized cathode current density, the optimized ion resistance, the optimized constant factor, the optimized limiting current density and the optimized open-circuit voltage of the Tariff line.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310231558.XA CN115966739B (en) | 2023-03-13 | 2023-03-13 | Fuel cell parameter identification method and system based on improved Hippocampus optimization algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310231558.XA CN115966739B (en) | 2023-03-13 | 2023-03-13 | Fuel cell parameter identification method and system based on improved Hippocampus optimization algorithm |
Publications (2)
Publication Number | Publication Date |
---|---|
CN115966739A CN115966739A (en) | 2023-04-14 |
CN115966739B true CN115966739B (en) | 2023-06-02 |
Family
ID=85888669
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310231558.XA Active CN115966739B (en) | 2023-03-13 | 2023-03-13 | Fuel cell parameter identification method and system based on improved Hippocampus optimization algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115966739B (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107122827A (en) * | 2017-04-28 | 2017-09-01 | 安徽工程大学 | A kind of RatSLAM algorithms based on DGSOM neutral nets |
CN108372857A (en) * | 2017-01-31 | 2018-08-07 | 通用汽车环球科技运作有限责任公司 | Autonomous driving system is occurred and the effective context aware of episodic memory review progress by event |
CN111506856A (en) * | 2020-03-10 | 2020-08-07 | 燕山大学 | Photovoltaic cell parameter identification method based on improved Harris eagle optimization algorithm |
CN112801163A (en) * | 2021-01-22 | 2021-05-14 | 安徽大学 | Multi-target feature selection method of mouse model hippocampal biomarker based on dynamic graph structure |
CN114492087A (en) * | 2022-04-02 | 2022-05-13 | 国网浙江省电力有限公司电力科学研究院 | Fault diagnosis method and device for proton exchange membrane fuel cell of hydrogen energy storage power station |
CN114976129A (en) * | 2022-05-13 | 2022-08-30 | 南京工业大学 | Application of novel crow search algorithm in proton exchange membrane fuel cell model parameter identification |
CN115392139A (en) * | 2022-10-27 | 2022-11-25 | 西北工业大学 | Fuel cell parameter identification method |
-
2023
- 2023-03-13 CN CN202310231558.XA patent/CN115966739B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108372857A (en) * | 2017-01-31 | 2018-08-07 | 通用汽车环球科技运作有限责任公司 | Autonomous driving system is occurred and the effective context aware of episodic memory review progress by event |
CN107122827A (en) * | 2017-04-28 | 2017-09-01 | 安徽工程大学 | A kind of RatSLAM algorithms based on DGSOM neutral nets |
CN111506856A (en) * | 2020-03-10 | 2020-08-07 | 燕山大学 | Photovoltaic cell parameter identification method based on improved Harris eagle optimization algorithm |
CN112801163A (en) * | 2021-01-22 | 2021-05-14 | 安徽大学 | Multi-target feature selection method of mouse model hippocampal biomarker based on dynamic graph structure |
CN114492087A (en) * | 2022-04-02 | 2022-05-13 | 国网浙江省电力有限公司电力科学研究院 | Fault diagnosis method and device for proton exchange membrane fuel cell of hydrogen energy storage power station |
CN114976129A (en) * | 2022-05-13 | 2022-08-30 | 南京工业大学 | Application of novel crow search algorithm in proton exchange membrane fuel cell model parameter identification |
CN115392139A (en) * | 2022-10-27 | 2022-11-25 | 西北工业大学 | Fuel cell parameter identification method |
Also Published As
Publication number | Publication date |
---|---|
CN115966739A (en) | 2023-04-14 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Priya et al. | A comprehensive review on parameter estimation techniques for Proton Exchange Membrane fuel cell modelling | |
Rezaie et al. | Model parameters estimation of the proton exchange membrane fuel cell by a Modified Golden Jackal Optimization | |
Ismaeel et al. | Gradient-based optimizer for parameter extraction in photovoltaic models | |
Özdemir | Optimal parameter estimation of polymer electrolyte membrane fuel cells model with chaos embedded particle swarm optimization | |
Bigdeli | Optimal management of hybrid PV/fuel cell/battery power system: A comparison of optimal hybrid approaches | |
Niu et al. | A biogeography-based optimization algorithm with mutation strategies for model parameter estimation of solar and fuel cells | |
Shi et al. | Multi-objective optimal design of hybrid renewable energy systems using preference-inspired coevolutionary approach | |
Wang et al. | An optimal configuration for hybrid SOFC, gas turbine, and Proton Exchange Membrane Electrolyzer using a developed Aquila Optimizer | |
Wang et al. | Application of co-evolution RNA genetic algorithm for obtaining optimal parameters of SOFC model | |
CN110210071B (en) | All-vanadium redox flow battery energy storage system operation optimization method based on genetic algorithm | |
Isa et al. | PEM fuel cell model parameters optimization using modified particle swarm optimization algorithm | |
Yakout et al. | Comparison among different recent metaheuristic algorithms for parameters estimation of solid oxide fuel cell: Steady-state and dynamic models | |
Rezk et al. | A novel strategy based on recent equilibrium optimizer to enhance the performance of PEM fuel cell system through optimized fuzzy logic MPPT | |
CN115392139B (en) | Fuel cell parameter identification method | |
Beshr et al. | Novel optimization technique of isolated microgrid with hydrogen energy storage | |
Zhang et al. | Application of coRNA-GA based RBF-NN to model proton exchange membrane fuel cells | |
Wang et al. | The utilization of adaptive African vulture optimizer for optimal parameter identification of SOFC | |
Fathy et al. | Proton exchange membrane fuel cell model parameters identification using Chaotically based-bonobo optimizer | |
Wai et al. | Installed capacity selection of hybrid energy generation system via improved particle‐swarm‐optimisation | |
CN110688762A (en) | Novel solid oxide fuel cell stack model construction method | |
Zhou et al. | Improved fish migration optimization method to identify PEMFC parameters | |
CN115966739B (en) | Fuel cell parameter identification method and system based on improved Hippocampus optimization algorithm | |
Erlin et al. | Parameter derivation of a proton exchange membrane fuel cell based on coevolutionary ribonucleic acid genetic algorithm | |
Jabbary et al. | Artificial intelligence-assisted optimization and multiphase analysis of polygon PEM fuel cells | |
Celtek | Estimation of PEMFC design parameters with social learning-based optimization |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |