Method and system for predicting water content of proton exchange membrane

By integrating artificial fish school and sparrow algorithms to form fused position update rules, the convolutional neural network efficiently predicts proton exchange membrane water content, addressing inaccuracies and inefficiencies in existing methods, enhancing fuel cell performance.

CN119067175AActive Publication Date: 2024-12-03SHANDONG UNIV
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202310640125.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-05-30
Publication Date
2024-12-03
Estimated Expiration
2043-05-30

AI Technical Summary

Technical Problem

Current methods for predicting proton exchange membrane water content in fuel cells are prone to local optima during training, leading to inaccurate results and inefficient parameter training, which affects the performance and efficiency of the fuel cell.

Method used

Integrate herding and tail-chasing behaviors from the artificial fish school algorithm into the follower and scout behaviors of the sparrow algorithm to form fused position update rules, training a convolutional neural network using internal resistance, temperature, and thickness of the proton exchange membrane as training data.

Benefits of technology

The combined algorithm prevents the convolutional neural network from falling into local optima, enabling efficient and accurate prediction of proton exchange membrane water content, thereby improving fuel cell performance.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119067175A_ABST
    Figure CN119067175A_ABST
Patent Text Reader

Abstract

The invention relates to a method and system for predicting the water content of a proton exchange membrane, and the method comprises the following steps: obtaining the internal resistance and temperature of a fuel cell membrane electrode, and the thickness of a fuel cell membrane, and predicting the corresponding water content of the proton exchange membrane based on a trained convolutional neural network; wherein the convolutional neural network takes the internal resistance and temperature of a fuel cell membrane electrode, the thickness of a proton exchange membrane and the pre-measured membrane water content as training data, and a clustering behavior and a rear-end collision behavior in an artificial fish swarm algorithm are respectively fused into a follower behavior and a reconnaissance behavior in a sparrow algorithm; and obtaining a fused follower behavior and reconnaissance behavior position updating rule, and training a convolutional neural network based on the fused position updating rule.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to the technical field of fuel cells, and in particular to a method and system for predicting the water content of a proton exchange membrane. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] Fuel cells use hydrogen and oxygen as fuel to release electrical energy, and the product is water, which is a green and clean energy source. When a fuel cell is running, its internal humidity is an important state parameter. Internal humidity refers to the water content of the proton exchange membrane. Its performance directly affects the proton transmission process, thereby affecting the efficiency of the fuel cell; it can also cause changes in internal resistance, causing changes in parameters such as output voltage, current, and power, affecting the output characteristics of the fuel cell; when the water content is lower than a certain range, "membrane drying" may occur, and when it exceeds a certain range, "flooding" may occur, which may cause the battery to fail in severe cases. Therefore, the humidity inside the fuel cell (usually the water content on the cathode side) is used as a control target to maintain the performance of the fuel cell.

[0004] The water content inside the fuel cell cannot be measured directly. Currently, it is obtained indirectly by calculating various parameters during the operation of the fuel cell. If a convolutional neural network is used to predict the water content, and the convolutional neural network needs to be trained to obtain accurate water content prediction results, it is easy to fall into the local optimum during training, resulting in inaccurate prediction results obtained from the training data. It takes a long time of training to meet the requirements, which indirectly makes the parameter training efficiency low. Summary of the invention

[0005] In order to solve the technical problems existing in the above-mentioned background technology, the present invention provides a method and system for predicting the water content of a proton exchange membrane, which integrates the herding behavior and tail-chasing behavior in the artificial fish school algorithm into the follower behavior and scout behavior in the sparrow algorithm, respectively, to obtain the fused follower behavior and scout behavior position update rules, and trains a convolutional neural network based on the fused position update rules.

[0006] In order to achieve the above object, the present invention adopts the following technical solution:

[0007] A first aspect of the present invention provides a method for predicting the water content of a proton exchange membrane, comprising the following steps:

[0008] Obtain the internal resistance and temperature of the fuel cell membrane electrode, as well as the thickness of the fuel cell membrane, and predict the corresponding proton exchange membrane water content based on the trained convolutional neural network;

[0009] Among them, the convolutional neural network uses the internal resistance, temperature, thickness of the proton exchange membrane and the pre-measured membrane water content of the fuel cell membrane electrode as training data, and integrates the clustering behavior and tail-chasing behavior in the artificial fish school algorithm into the follower behavior and scout behavior in the sparrow algorithm respectively, and obtains the fused follower behavior and scout behavior position update rules, and trains the convolutional neural network based on the fused position update rules.

[0010] The clustering behavior in the artificial fish algorithm is integrated into the follower position update rule in the sparrow algorithm, and the fused follower position update rule is obtained as follows:

[0011]

[0012] In the formula, The best position for the discoverer. is the global worst position in the current iteration, A + =A T (AA T ) -1 , and A is a 1×d matrix whose all elements are randomly 1 or -1, Q is a random number that obeys the normal distribution as a whole, L is a matrix whose all elements are 1, Rand() is a random number that obeys the uniform distribution between -1 and 1, and ω1 and ω2 represent weight coefficients.

[0013] The tail-chasing behavior in the artificial fish school is integrated into the scout position update rule in the sparrow algorithm, and the fused scout position update rule is obtained as follows:

[0014]

[0015] In the above formula, is the global optimal position, β is the step size control variable which obeys the normal distribution with zero mean and unit variance, K is a random number between 1 and -1, and f n is the current sparrow’s fitness value, f b is the global optimal fitness value, f w is the global worst fitness value, ε is a sufficiently small normal number, Rand() is a random number between -1 and 1 that obeys a uniform distribution, and ω1 and ω2 represent weight coefficients.

[0016] The internal resistance, temperature and thickness of the proton exchange membrane of the fuel cell membrane electrode are used as input, and the pre-measured membrane water content is used as output to train the convolutional neural network.

[0017] The internal resistance of the fuel cell membrane electrode is measured by the impedance method, specifically: using a sine wave as an excitation signal to disturb, measuring its response signal, and processing and analyzing the response signal to obtain the corresponding impedance.

[0018] The water content of the fuel cell membrane is measured by a drying weighing method, specifically: the fuel cell is placed in a drying box for drying, and the water content of the fuel cell membrane is obtained by measuring the weight difference before and after drying.

[0019] In the sparrow algorithm, each individual in the sparrow population corresponds to a feasible solution to the optimization problem. Suppose the population size is N. The follower will approach the discoverer individual with a high fitness value and forage for food in each iteration. When the fitness value of the follower at its position is better than that of the discoverer, that is, i≤N / 2, the follower position will replace the discoverer position. When the follower is in an extremely hungry state, that is, i>N / 2, the follower will change its position to forage for food in other areas.

[0020] A second aspect of the present invention provides a system for implementing the above method, comprising:

[0021] The water content prediction module is configured to: obtain the internal resistance and temperature of the fuel cell membrane electrode and the thickness of the fuel cell membrane, and predict the corresponding proton exchange membrane water content based on the trained convolutional neural network;

[0022] Among them, the convolutional neural network uses the internal resistance, temperature, thickness of the proton exchange membrane and the pre-measured membrane water content of the fuel cell membrane electrode as training data, and integrates the clustering behavior and tail-chasing behavior in the artificial fish school algorithm into the follower behavior and scout behavior in the sparrow algorithm respectively, and obtains the fused follower behavior and scout behavior position update rules, and trains the convolutional neural network based on the fused position update rules.

[0023] A third aspect of the present invention provides a computer-readable storage medium.

[0024] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps in the above-mentioned method for predicting the water content of a proton exchange membrane.

[0025] A fourth aspect of the present invention provides a computer device.

[0026] A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps in the above-mentioned method for predicting the water content of a proton exchange membrane are implemented.

[0027] Compared with the prior art, one or more of the above technical solutions have the following beneficial effects:

[0028] 1. Taking the internal resistance, temperature, thickness of the proton exchange membrane and the pre-measured water content of the fuel cell membrane electrode as training data, the clustering behavior and tail-chasing behavior in the artificial fish school algorithm are respectively integrated into the follower behavior and scout behavior in the sparrow algorithm to obtain the fused follower behavior and scout behavior position update rules, and train the convolutional neural network based on the fused position update rules, so that the convolutional neural network will no longer fall into the local optimum during training, and thus the required parameters can be obtained efficiently.

[0029] 2. Integrate the clustering behavior in the artificial fish swarm algorithm into the follower behavior in the sparrow algorithm, and integrate the tail-chasing behavior in the artificial fish swarm algorithm into the scout behavior in the sparrow algorithm to obtain a new position update rule, thereby improving the performance of the sparrow algorithm and forming a combined algorithm. Based on the combined algorithm, the convolutional neural network is trained so that the convolutional neural network no longer falls into the local optimum. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0031] Figure 1 It is a schematic diagram of a proton exchange membrane water content prediction process provided by one or more embodiments of the present invention. DETAILED DESCRIPTION

[0032] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0033] It should be noted that the following detailed descriptions are exemplary and are intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0034] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0035] The following embodiment provides a method and system for predicting the water content of a proton exchange membrane, combining the sparrow algorithm and the artificial fish swarm algorithm, and using the combined algorithm to optimize a convolutional neural network. The newly obtained convolutional neural network is used to train the database of the internal resistance, temperature, thickness of the proton exchange membrane and the water content of the fuel cell membrane electrode. After the training is completed, the internal resistance and temperature of the fuel cell membrane electrode are collected, and the thickness of the fuel cell membrane is obtained. The corresponding proton exchange membrane water content is predicted based on the trained convolutional neural network.

[0036] Embodiment 1:

[0037] like Figure 1 As shown, the method for predicting the water content of a proton exchange membrane comprises the following steps:

[0038] Obtain the internal resistance and temperature of the fuel cell membrane electrode, as well as the thickness of the fuel cell membrane, and predict the corresponding proton exchange membrane water content based on the trained convolutional neural network;

[0039] Among them, the convolutional neural network uses the internal resistance, temperature, thickness of the proton exchange membrane and the pre-measured membrane water content of the fuel cell membrane electrode as training data, and integrates the clustering behavior and tail-chasing behavior in the artificial fish school algorithm into the follower behavior and scout behavior in the sparrow algorithm respectively, and obtains the fused follower behavior and scout behavior position update rules, and trains the convolutional neural network based on the fused position update rules.

[0040] Specific:

[0041] The herding behavior and tail-chasing behavior in the artificial fish swarm algorithm are respectively integrated into the follower behavior and scout behavior in the sparrow algorithm to obtain a combined algorithm, which is then used to optimize the convolutional neural network.

[0042] The internal resistance of the fuel cell membrane electrode is measured by the AC impedance method, and the temperature at that time is measured at the same time; the water content of the fuel cell proton exchange membrane is obtained by the drying weighing method, and a database of the internal resistance, temperature, proton exchange membrane thickness and membrane water content of the fuel cell membrane electrode is obtained.

[0043] The optimized convolutional neural network was used to train the database of fuel cell membrane electrode internal resistance, temperature, proton exchange membrane thickness and membrane water content, and a method for predicting proton exchange membrane water content was obtained. The internal resistance and temperature of the fuel cell membrane electrode were collected, and the thickness of the fuel cell membrane was obtained. The corresponding proton exchange membrane water content was predicted based on the trained convolutional neural network.

[0044] The proton exchange membrane fuel cell has components such as a current collecting plate, a bipolar plate, a membrane electrode and a sealing gasket, wherein the membrane electrode of the proton exchange membrane fuel cell includes a gas diffusion layer, a microporous layer, a catalyst layer and a proton exchange membrane.

[0045] The method for measuring the internal resistance of the fuel cell membrane electrode is the AC impedance method. This method uses a small sine wave as an excitation signal to disturb the system, then measures its response signal, processes and analyzes the response signal, thereby obtaining the corresponding impedance and measuring its temperature at the same time.

[0046] The water content of the fuel cell membrane is measured by the drying weighing method, that is, the fuel cell is placed in a drying box for drying, and the water content of the fuel cell membrane is obtained by measuring the weight before and after drying. The data of the fuel cell's internal resistance, temperature, thickness of the proton exchange membrane and its membrane water content are obtained as training data.

[0047] The combined algorithm integrates the flocking behavior of the artificial fish swarm algorithm into the follower behavior of the sparrow algorithm, and integrates the tail-chasing behavior of the artificial fish swarm algorithm into the scout behavior of the sparrow algorithm, and obtains new position update rules to improve the performance of the sparrow algorithm, forming a combined algorithm.

[0048] In the sparrow algorithm, each individual in the sparrow population represents a feasible solution to the corresponding optimization problem. Suppose the population size is N, and the position of the nth sparrow is Where d represents the dimension of the optimization variable, and the element value of each dimension is the value of the corresponding optimization variable.

[0049] In each iteration, the follower will approach the discoverer individual with a high fitness value and forage for food. When the fitness value of the follower at its position is better than that of the discoverer (i≤N / 2), the follower position will replace the discoverer position. When the follower is in an extremely hungry state (i>N / 2), the follower will change its position to forage for food in other areas. The follower position update rule is:

[0050]

[0051] In the above formula, The best position for the discoverer. is the global worst position in the current iteration, A + =A T (AA T ) -1 , and A is a 1×d matrix whose elements are randomly 1 or -1, Q is a random number that obeys the normal distribution as a whole, and L is a matrix whose elements are all 1.

[0052] The sparrow population will randomly select some individuals in the population as scouts. When the scouts sense danger, the individuals at the edge of the area will move to the safe area, and the sparrow individuals in the center area will move randomly. The position update rule is:

[0053]

[0054] In the above formula, is the global optimal position, β is the step size control variable which obeys the normal distribution with zero mean and unit variance, K is a random number between 1 and -1, and f n is the current sparrow’s fitness value, f b is the global optimal fitness value, f w is the global worst fitness value, and ε is a sufficiently small positive constant.

[0055] Artificial fish swarm algorithm, there are N artificial fish in a d-dimensional search space, the state position of the artificial fish is represented by the vector X = (x1, x2, ..., x d ) means, ||X i -X j || represents the spatial distance between two artificial fish individuals, the visual field of the artificial fish is Visual, the crowding degree of the artificial fish school is represented by the crowding factor δ, the moving step length of the artificial fish is step, and the food concentration at the location of the artificial fish is Y=f(x).

[0056] Fish groups are naturally capable of grouping behavior. When encountering natural enemies and foraging in their living environment, they will group together to increase their survival probability and foraging efficiency. i The artificial fish, in d i,j <Count the number of other artificial fish individuals n within the Visual range f , and find its average state X C :

[0057]

[0058] If Y C / n f >δ*Y i If true, then in the optimization space, state X C A higher fitness can be obtained at the state X, and more artificial fish individuals can be accommodated. Artificial fish individuals can move towards state X. C If the swarm is not in the same place, they will gather together, otherwise they will continue to forage. The position update is:

[0059]

[0060] In the above formula, Indicates that the status is X i The t+1th iteration of the artificial fish, Indicates that the status is X i For the tth iteration of the artificial fish, Rand() is a random number between -1 and 1 that follows a uniform distribution.

[0061] Fish groups tend to move towards food and away from predators. When some individuals in the group move in a certain direction, other individuals will follow them. i The artificial fish, in d i,j <Count the number of other artificial fish individuals n within the Visual range f , and find the individual X with the highest fitness within this range j , whose fitness value is Y j If Y j / n f >δ*Y i , then in the optimization space X j The fitness is high and there is still space for the artificial fish to continue to gather. j Otherwise, continue to forage.

[0062]

[0063] Combine the sparrow algorithm with the artificial fish algorithm. Integrate the swarming behavior in the artificial fish algorithm into the follower position update rule in the sparrow algorithm, and obtain the new follower position update rule:

[0064]

[0065] In the formula, The best position for the discoverer. is the global worst position in the current iteration, A + =A T (AA T ) -1 , and A is a 1×d matrix whose all elements are randomly 1 or -1, Q is a random number that obeys the normal distribution as a whole, L is a matrix whose all elements are 1, Rand() is a random number that obeys a uniform distribution between -1 and 1, and ω1 and ω2 represent weight coefficients.

[0066] The tail-chasing behavior in the artificial fish school is integrated into the scout position update rule in the sparrow algorithm, and the new scout position update rule is obtained as follows:

[0067]

[0068] In the above formula, is the global optimal position, β is the step size control variable which obeys the normal distribution with zero mean and unit variance, K is a random number between 1 and -1, and f n is the current sparrow’s fitness value, f b is the global optimal fitness value, f wis the global worst fitness value, ε is a sufficiently small normal number, Rand() is a random number between -1 and 1 that obeys a uniform distribution, and ω1 and ω2 represent weight coefficients.

[0069] This results in a combinatorial algorithm.

[0070] Convolutional neural network (CNN) constructs a network structure based on local connection, weight sharing and downsampling, including input layer, alternating convolution layer and downsampling layer, fully connected layer and output layer. The obtained combination algorithm is used to train the parameters in the convolutional neural network.

[0071] Among them, the parameters include the convolution kernel weight w in the convolution layer c,k (k=1,2,...,Nc), bias b c,k (k=1,2,...,Nc), fully connected layer weight w L4 , bias b L4 , Nc represents the number of convolution kernels. Thus, an improved convolutional neural network based on the combination algorithm is obtained. Then, the improved convolutional neural network is used to train and test the database of fuel cell internal resistance, temperature, proton exchange membrane thickness and membrane water content.

[0072] After the training is completed, the internal resistance and temperature of the fuel cell membrane electrode are collected, and the thickness of the fuel cell membrane is obtained. The corresponding proton exchange membrane water content is predicted based on the trained convolutional neural network.

[0073] Embodiment 2:

[0074] A system for implementing the above method comprises:

[0075] The water content prediction module is configured to: obtain the internal resistance and temperature of the fuel cell membrane electrode and the thickness of the fuel cell membrane, and predict the corresponding proton exchange membrane water content based on the trained convolutional neural network;

[0076] Among them, the convolutional neural network uses the internal resistance, temperature, thickness of the proton exchange membrane and the pre-measured membrane water content of the fuel cell membrane electrode as training data, and integrates the herding behavior and tail-chasing behavior in the artificial fish school algorithm into the follower behavior and scout behavior in the sparrow algorithm respectively, and obtains the fused follower behavior and scout behavior position update rules, and trains the convolutional neural network based on the fused position update rules.

[0077] Embodiment three:

[0078] This embodiment provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the steps in the method for predicting the water content of a proton exchange membrane as described in the first embodiment above are implemented.

[0079] Embodiment 4:

[0080] This embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the program, the steps in the method for predicting the water content of a proton exchange membrane as described in the first embodiment are implemented.

[0081] The steps or modules involved in the above embodiments 2 to 4 correspond to those in embodiment 1. For the specific implementation, please refer to the relevant description of embodiment 1. The term "computer-readable storage medium" should be understood as a single medium or multiple media including one or more instruction sets; it should also be understood to include any medium that can store, encode or carry an instruction set for execution by a processor and enable the processor to execute any method in the present invention.

[0082] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for predicting water content of a proton exchange membrane, characterized in that: The following steps are involved: Obtain the internal resistance and temperature of the fuel cell membrane electrode, as well as the thickness of the fuel cell membrane, and predict the corresponding proton exchange membrane water content based on the trained convolutional neural network; Among them, the convolutional neural network uses the internal resistance, temperature, thickness of the proton exchange membrane and the pre-measured membrane water content of the fuel cell membrane electrode as training data, and integrates the herding behavior and tail-chasing behavior in the artificial fish school algorithm into the follower behavior and scout behavior in the sparrow algorithm respectively, and obtains the fused follower behavior and scout behavior position update rules, and trains the convolutional neural network based on the fused position update rules.

2. The method for predicting water content of a proton exchange membrane according to claim 1, characterized in that: The clustering behavior in the artificial fish algorithm is integrated into the follower position update rule in the sparrow algorithm, and the fused follower position update rule is obtained as follows: In the formula, The best position for the discoverer. is the global worst position in the current iteration, A + =A T (AA T ) -1 , and A is a 1×d matrix whose all elements are randomly 1 or -1, Q is a random number that obeys the normal distribution as a whole, L is a matrix whose all elements are 1, Rand() is a random number that obeys the uniform distribution between -1 and 1, and ω1 and ω2 represent weight coefficients.

3. The method for predicting water content of a proton exchange membrane according to claim 1, characterized in that: The tail-chasing behavior in the artificial fish school is integrated into the scout position update rule in the sparrow algorithm, and the fused scout position update rule is obtained as follows: In the above formula, is the global optimal position, β is the step size control variable which obeys the normal distribution with zero mean and unit variance, K is a random number between 1 and -1, and f n is the current sparrow’s fitness value, f b is the global optimal fitness value, f w is the global worst fitness value, ε is a sufficiently small normal number, Rand() is a random number between -1 and 1 that obeys a uniform distribution, and ω1 and ω2 represent weight coefficients.

4. The method for predicting water content of a proton exchange membrane according to claim 1, characterized in that: The internal resistance, temperature and thickness of the proton exchange membrane of the fuel cell membrane electrode are used as input, and the pre-measured membrane water content is used as output to train the convolutional neural network.

5. The method for predicting water content of a proton exchange membrane according to claim 4, characterized in that: The internal resistance of the fuel cell membrane electrode is measured by the impedance method, specifically: using a sine wave as an excitation signal to disturb, measuring its response signal, and processing and analyzing the response signal to obtain the corresponding impedance.

6. The method for predicting water content of a proton exchange membrane according to claim 4, characterized in that: The water content of the fuel cell membrane is measured by a drying weighing method, specifically: the fuel cell is placed in a drying box for drying, and the water content of the fuel cell membrane is obtained by measuring the weight difference before and after drying.

7. The method for predicting water content of a proton exchange membrane according to claim 1, characterized in that: In the sparrow algorithm, each individual in the sparrow population corresponds to a feasible solution to the optimization problem. Suppose the population size is N. The follower will approach the discoverer individual with a high fitness value and forage for food in each iteration. When the fitness value of the follower at its position is better than that of the discoverer, that is, i≤N / 2, the follower position will replace the discoverer position. When the follower is in an extremely hungry state, that is, i>N / 2, the follower will change its position to forage for food in other areas.

8. A proton exchange membrane water content prediction system, characterized in that: include: The water content prediction module is configured to: obtain the internal resistance and temperature of the fuel cell membrane electrode and the thickness of the fuel cell membrane, and predict the corresponding proton exchange membrane water content based on the trained convolutional neural network; Among them, the convolutional neural network uses the internal resistance, temperature, thickness of the proton exchange membrane and the pre-measured membrane water content of the fuel cell membrane electrode as training data, and integrates the herding behavior and tail-chasing behavior in the artificial fish school algorithm into the follower behavior and scout behavior in the sparrow algorithm respectively, and obtains the fused follower behavior and scout behavior position update rules, and trains the convolutional neural network based on the fused position update rules.

9. A computer-readable storage medium having a computer program stored thereon, wherein when the program is executed by a processor, the steps of the method for predicting the water content of a proton exchange membrane as claimed in any one of claims 1 to 7 are implemented.

10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the method for predicting the water content of a proton exchange membrane as claimed in any one of claims 1 to 7 are implemented.

Citation Information

Patent Citations

  • Personnel evacuation method, device and equipment under cruise ship fire and storage medium

    CN115689489A

  • Distributed multi-layer particle swarm optimization based cognitive network

    US20140214742A1