Power battery SOH prediction method and system based on vulture combination algorithm

Abstract

The invention provides a power battery SOH (state of health) prediction method and system based on a vulture combination algorithm, and the global search capability of the vulture algorithm is enhanced through a spiral flight behavior executed by the vulture, a prey consumption strategy and an optimal value of a snake vulture algorithm, and an escape strategy and a reverse learning strategy based on the snake vulture algorithm. Based on the obtained SOH and the data set of the charging and discharging times and the charging and discharging parameters, VMD parameters and SVM parameters are optimized through the vulture combination algorithm, an SOH prediction model is constructed, the charging and discharging times and the charging and discharging parameters which are collected in real time are input into the prediction model, and a specific SOH value can be obtained. According to the power battery SOH prediction method based on the snake vulture algorithm, a spiral flight behavior is executed through the vulture, the optimal value is searched through a prey consumption strategy of the snake vulture algorithm, the global search ability of the vulture algorithm is enhanced based on an escape strategy and a reverse learning strategy of the snake vulture algorithm, and a more reliable and efficient solution can be provided for power battery SOH prediction.

Description

Technical Field

[0001] The present invention belongs to the technical field of power battery SOH prediction, and in particular relates to a power battery SOH prediction method and system based on a vulture combination algorithm. 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] With the rapid development of new energy vehicles, new energy engineering machinery and new energy agricultural machinery, the power battery, as the core energy source of these devices, has become particularly critical for accurate assessment of its state of health (SOH). Power batteries not only support the continuous driving of new energy vehicles, the efficient operation of engineering machinery and the stable operation of agricultural machinery, but also become an important indicator for measuring equipment performance and service life due to their reliability and durability requirements during long-term operation.

[0004] However, as the battery is used for a longer time, it will undergo a series of physical and chemical changes inside, causing the battery capacity to gradually decrease and the performance to gradually decline. This decline in battery performance is undoubtedly a huge challenge for new energy devices that rely on a stable energy supply.

[0005] Therefore, in-depth research on the state of power battery SOH and the development of efficient and accurate evaluation methods are of far-reaching significance and value for ensuring that new energy vehicles, new energy engineering machinery and new energy agricultural machinery can operate for a long time and reliably. Summary of the invention

[0006] In order to solve the above problems, the present invention proposes a method and system for predicting the SOH of a power battery based on a vulture combination algorithm. The present invention uses the spiral flight behavior of vultures and the prey consumption strategy of the secretary vulture algorithm to find the local optimal value, and based on the escape strategy and reverse learning strategy of the secretary vulture algorithm, strengthens the global search capability of the vulture algorithm, which can provide a more reliable and efficient solution for the prediction of the SOH of the power battery.

[0007] According to some embodiments, the present invention adopts the following technical solutions:

[0008] A method for predicting SOH of a power battery based on a vulture combination algorithm comprises the following steps:

[0009] Obtain the number of charge and discharge times and charge and discharge parameters, and construct a data set;

[0010] Based on the data set, the vulture combination algorithm is used to optimize the parameters of the variational mode decomposition algorithm and the parameters of the support vector machine to build a SOH prediction model;

[0011] The charge and discharge times and charge and discharge parameters are acquired in real time, and the predicted SOH value is obtained by using the SOH prediction model based on the real-time acquired data;

[0012] The vulture combination algorithm uses vultures to perform spiral flight behavior to find a first optimal value, introduces the first optimal value into the prey consumption strategy of the secretary vulture algorithm to obtain a second optimal value, selects the best value between the first optimal value and the second optimal value, and iterates the above optimization process until an optimal solution that meets the requirements is obtained;

[0013] When the optimization process falls into a local optimum, the escape strategy and reverse learning strategy of the snake vulture algorithm are used to jump out of the local optimum and continue to look for a better solution.

[0014] As an optional implementation, the process of obtaining the number of charge and discharge times and charge and discharge parameters includes charging and discharging at a set temperature with a predetermined current and voltage as a charge / discharge test cycle, which is repeated continuously until the battery capacity is reduced to a set value, thereby obtaining a data set of SOH, the number of charge and discharge times and the charge and discharge parameters.

[0015] As an optional implementation, the process of using a vulture to perform a spiral flight behavior to find the first optimal value includes: performing a spiral flight behavior through a vulture algorithm to find the first optimal value, denoted as x best , the formula is as follows:

[0016]

[0017] in, is the position of the ith individual at time t+1, is the position of the i-th individual at time t, and t is the number of iterations; represents the optimal individual at time t, r5 and r6 are both random numbers between 0 and 1.

[0018] As an optional implementation, the process of introducing the first optimal value into the prey consumption strategy of the secretary vulture algorithm includes: introducing the first optimal value x best Introduced into the process of consuming prey by the secretary vulture algorithm, the formula is as follows:

[0019] RB=randn(1,Dim)

[0020]

[0021] Where RB is Brownian motion; randn(1,Dim) represents an array of dimension 1×Dim randomly generated from a standard normal distribution; is the current position of the i-th j-dimensional secretary bird in this stage; The current optimal position of the secretary bird; represents the current position of the i-th j-dimensional secretary bird at time t;

[0022] The second optimal value is found through the prey consumption strategy of the secretary vulture algorithm, denoted as x' best .

[0023] As an optional implementation, the process of iterating the above optimization process until the optimal solution that meets the requirements is obtained includes: taking the first optimal value x best and the second optimal value x' best The optimal value of the two judge Whether the consecutive times that the value is less than the set value exceeds the predetermined times, if so, it falls into the local optimum, if not, it returns to the optimization process until it falls into the local optimum.

[0024] As an optional implementation method, when the optimization process falls into a local optimum, the escape strategy and reverse learning strategy of the Snake Vulture algorithm are adopted. The process of jumping out of the local optimum includes: executing the escape strategy of the Snake Vulture algorithm, and the formula is as follows:

[0025]

[0026] The obtained results are introduced into the reverse learning strategy, and the formula is as follows:

[0027] K = round(1+rand(1,1))

[0028]

[0029] in, is the current position of the i-th j-dimensional secretary bird in this stage; sx i,j represents the current position of the i-th j-dimensional secretary bird; R2 represents the array of dimension 1×Dim generated randomly from the normal distribution; sx random is the iterative random candidate solution position; K represents a random selection of integers 1 or 2; X COBL is the inverse solution generated by COBL; ub and lb are the upper and lower bounds of the search space respectively; rand is a random function that obeys uniform distribution;

[0030] Execute the above strategy a set number of times to find the optimal solution.

[0031] As an optional implementation, the process of using the vulture combination algorithm to optimize the parameters of the variational modal decomposition algorithm includes using the vulture combination algorithm to optimize the number of modal decompositions K and the penalty factor α of the variational modal decomposition algorithm, using the fuzzy entropy of each modal component obtained by the variational modal decomposition algorithm of the data set as the fitness function, and finding the optimal combination of [K, α] of the variational modal decomposition algorithm.

[0032] As an optional implementation method, the process of optimizing the parameters of the support vector machine using the vulture combination algorithm includes optimizing the parameters C and g of the support vector machine using the vulture combination algorithm, and then training with a data set decomposed by a variational mode decomposition algorithm, using the root mean square error of the predicted and measured SOH as the fitness value, obtaining the hyperparameter combination that optimizes the support vector machine estimation effect, and forming a SOH prediction model.

[0033] A prediction system for power battery SOH based on vulture combination algorithm, comprising:

[0034] A data acquisition module is configured to acquire the number of charge and discharge times and charge and discharge parameters and construct a data set;

[0035] A prediction model building module is configured to use a vulture combination algorithm to optimize the parameters of the variational mode decomposition algorithm and the parameters of the support vector machine based on the data set to build a SOH prediction model;

[0036] The prediction module is configured to obtain the number of charge and discharge times and charge and discharge parameters in real time, and obtain a predicted SOH value using a SOH prediction model based on the data obtained in real time;

[0037] The vulture combination algorithm uses vultures to perform spiral flight behavior to find the first optimal value, introduces the first optimal value into the prey consumption strategy of the secretary vulture algorithm to obtain the second optimal value, selects the optimal value between the first optimal value and the second optimal value, and iterates the above optimization process until the optimal solution that meets the requirements is obtained; when the optimization process falls into a local optimum, the escape strategy and reverse learning strategy of the secretary vulture algorithm are used to jump out of the local optimum and continue to find a better solution.

[0038] An electronic device comprises a memory and a processor, and computer instructions stored in the memory and executed on the processor. When the computer instructions are executed by the processor, the steps in the above method are completed.

[0039] Compared with the prior art, the present invention has the following beneficial effects:

[0040] The present invention uses the spiral flight behavior of vultures and the prey consumption strategy of the secretary vulture algorithm to quickly find the local optimum; the present invention also introduces a reverse learning strategy to generate a large number of inverse solutions, so that the algorithm has good random search performance in the exploration stage, which helps to provide more population diversity in the middle and late stages of the algorithm and prevent the vulture algorithm from falling into the local optimum too early. At the same time, the escape strategy of the secretary vulture algorithm helps to jump out of the local optimum and strengthen the global search capability of the vulture algorithm.

[0041] The present invention is based on the acquired data set of SOH, charge and discharge times and charge and discharge parameters, adopts the vulture combination algorithm to optimize the parameters of VMD and SVM, constructs an SOH prediction model, and inputs the charge and discharge times and charge and discharge parameters collected in real time into the prediction model to obtain a specific SOH value. Thus, a prediction method and system for the SOH of a power battery based on the vulture combination algorithm are obtained, which provides a more reliable and efficient solution for the prediction of the SOH of a power battery.

[0042] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] 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.

[0044] Figure 1 The present invention is a flowchart of a method for predicting the SOH of a power battery based on a vulture combination algorithm in an embodiment. DETAILED DESCRIPTION

[0045] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0046] It should be noted that the following detailed descriptions are all illustrative and 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.

[0047] 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.

[0048] In the absence of conflict, the embodiments in this application and the features in the embodiments may be combined with each other.

[0049] Embodiment 1

[0050] This embodiment discloses a method for predicting the SOH of a power battery based on a vulture combination algorithm, including:

[0051] Obtain the number of charge and discharge times and charge and discharge parameters, and construct a data set;

[0052] Based on the data set, the vulture combination algorithm is used to optimize the parameters of the variational mode decomposition algorithm and the parameters of the support vector machine to build a SOH prediction model;

[0053] The charge and discharge times and charge and discharge parameters are acquired in real time, and the predicted SOH value is obtained by using the SOH prediction model based on the real-time acquired data;

[0054] The vulture combination algorithm uses vultures to perform spiral flight behavior to find a first optimal value, introduces the first optimal value into the prey consumption strategy of the secretary vulture algorithm to obtain a second optimal value, selects the best value between the first optimal value and the second optimal value, and iterates the above optimization process until an optimal solution that meets the requirements is obtained;

[0055] When the optimization process falls into a local optimum, the escape strategy and reverse learning strategy of the snake vulture algorithm are used to jump out of the local optimum and continue to look for a better solution.

[0056] The following is a detailed description of this embodiment:

[0057] First, the power battery of this embodiment can be used for new energy vehicles, new energy engineering machinery and new energy agricultural machinery, including hybrid and electric vehicles, hybrid and electric bulldozers, hybrid and electric loaders, hybrid and electric excavators, hybrid and electric tractors, etc., and the power battery is subjected to SOH test. The experimental process is to charge and discharge the battery with a set current and voltage at a set temperature, and repeat the above process as a charge / discharge test cycle until the battery capacity is reduced to a set value (such as 0.80Ah), thereby obtaining a data set of SOH, charge and discharge times and charge and discharge parameters.

[0058] The vulture algorithm process is mainly divided into the following four stages:

[0059] Under natural conditions, vultures are divided into three groups according to their species and living habits. If different feasibility schemes are used to measure each vulture group, the best feasible solution is the first group, followed by the second group. In addition to the two groups of vultures mentioned above, the remaining vultures are divided into three teams.

[0060] Stage 1: Population classification and selection of leading vultures.

[0061] In the vulture model, vultures with higher fitness will find food first. According to the fitness value, the vultures are divided into three groups. Each group selects one from the first and second groups, and then leads the entire group to find food as the leader:

[0062]

[0063] Where t is the number of iterations; represents the optimal individual at time t; is the first group of optimal individuals at time t; represents the second group of optimal individuals at time t; α and β are quantitative parameters, where α+β=1, α∈(0,1), β∈(0,1); represents the parameters of individual i at the tth iteration (may be position or speed, etc.); m represents the number of individuals in the population; is the fitness value of the i-th individual at time t. The vulture selects the best individual to lead the population search through the above formula.

[0064] When α is close to 1 and β is close to 0, Vulture tends to enhance local search. When α is close to 0 and β is close to 1, the diversity of algorithm search is increased, which is conducive to finding the global optimal solution.

[0065] Phase 2: Calculate the hunger level of the vulture population.

[0066] In the vulture algorithm, the hunger value is used to measure the hunger of the vulture, and the exploration and development stages are selected according to the hunger of the vulture itself. The hunger value is shown in the following formula:

[0067]

[0068] In the formula, represents the hunger degree of the i-th individual in the t-th iteration; is a random number between 0 and 1; h is a random number between [-1,1]; t is the current iteration number; T is the total iteration number; τ t It can be obtained by the following formula:

[0069]

[0070] In the formula, m t is a random number in [-2,2]; w is a constant of 2.5. The smaller w is, the greater the probability that the algorithm will enter the development stage; when When , the individual enters the exploration stage; when When the individual enters the development stage.

[0071] Phase 3: Search using exploration strategies.

[0072] The selection of exploration behavior is determined by a certain parameter p1 between [0,1].

[0073]

[0074] In the formula, is the position of the ith individual at time t+1; r1, r2, rand are all random numbers in [0, 1]; ub and lb represent the upper and lower bounds of the solution space respectively; is the distance between the i-th individual and the current optimal or suboptimal individual in the t-th iteration.

[0075]

[0076] In the formula, C is a random number between 0 and 2; is the position of the ith individual at time t.

[0077] Stage 4: The vulture performs a spiral flight behavior.

[0078] when When the vulture is flying in a spiral, the position update formula is expressed as:

[0079]

[0080] Where r5 and r6 are both random numbers between 0 and 1.

[0081] Construct a secretary bird algorithm model: According to the habits of secretary birds, the survival skills of secretary birds are divided into hunting strategies and escape strategies; hunting strategies include finding prey and consuming prey.

[0082] Initialize the position of the secretary bird. The initial position can be expressed as:

[0083] SX i,j =lb j +r×(ub j -lb j )

[0084] i=1,2,...,M,j=1,2,...,Dim

[0085] Among them, SX i,j represents the current position of the i-th j-dimensional secretary bird; r represents a random number between 0 and 1; lb j andub j are the lower and upper limits of the search space respectively; M is the number of secretary birds; Dim is the dimension.

[0086] Finding prey: Simulate the secretary bird's search for prey, using its incredibly sharp eyesight to track and find snakes hidden in the grass. Execute the secretary bird algorithm's prey-finding strategy, and the position update method is shown in the following formula:

[0087]

[0088] In the formula, is the current position of the i-th j-dimensional secretary bird; sx i,j represents the current position of the i-th j-dimensional secretary bird; sx random_1 and sx random_2is the iterative random candidate solution position; R1 represents a randomly generated array of dimension 1×Dim in the interval [0,1], where Dim is the dimension of the solution space; represents the new state of the i-th secretary bird; F i new,P1 Indicates the fitness value of the objective function in the new state; F i Represents the fitness value of the objective function in the above state.

[0089] Consuming prey: Secretary birds are not in a hurry to pounce on the snake. They use agile steps and mobility to observe the snake, and by keenly judging the snake's movements, they gradually circle, jump, and provoke the snake to consume its stamina. The position update method is shown in the following formula:

[0090] RB=randn(1,Dim)

[0091]

[0092] Where RB is Brownian motion; randn(1,Dim) represents an array of dimension 1×Dim randomly generated from a standard normal distribution (mean value is 0 and standard deviation is 1); is the current position of the i-th j-dimensional secretary bird; The current optimal position of the secretary bird; represents the current position of the i-th j-dimensional secretary bird at time t;

[0093] Escape strategy: Secretary birds have many natural enemies, such as eagles, foxes, and jackals. When threatened, they will flee to avoid the attacks of their natural enemies. The escape strategy of the Secretary Bird algorithm is implemented, and the position update method is shown in the following formula:

[0094]

[0095] K = round(1+rand(1,1))

[0096] In the formula, is the current position of the i-th j-dimensional secretary bird; sx i,j represents the current position of the i-th j-dimensional secretary bird; R2 represents the array of dimension 1×Dim generated randomly from the normal distribution; sx random is the iterative random candidate solution position; K represents a random selection of an integer 1 or 2.

[0097] In this embodiment, if Figure 1 As shown, first, the spiral flight behavior is performed by the vulture algorithm, and the formula is as follows:

[0098]

[0099] Find the optimal value, denoted as x best .

[0100] Then, x best Introduced into the process of consuming prey by the secretary vulture algorithm, the formula is as follows:

[0101] RB=randn(1,Dim)

[0102]

[0103] Where RB is Brownian motion; randn(1,Dim) represents an array of dimension 1×Dim randomly generated from a standard normal distribution (mean value is 0 and standard deviation is 1); is the current position of the i-th j-dimensional secretary bird; The current optimal position of the secretary bird; represents the current position of the i-th j-dimensional secretary bird at time t;

[0104] Find the optimal value, recorded as x' best .

[0105] Finally, select the best value of the two judge Whether the consecutive times exceeds a first set value, i.e., NY times. In this implementation, the first set value is 20, i.e., NY=20;

[0106] If not, it returns to the spiral flight behavior of the vulture algorithm and the prey consumption strategy of the secretary vulture algorithm until <1% consecutive times> 20, at this time the algorithm falls into the local optimum, and the escape strategy and reverse learning strategy of the secretary vulture algorithm are executed.

[0107] In order to prevent the algorithm from falling into the local optimum, the escape strategy of the Snake Eagle algorithm is executed. The formula is as follows:

[0108]

[0109] The obtained results are introduced into the reverse learning strategy. The formula is as follows:

[0110] K = round(1+rand(1,1))

[0111]

[0112] In the formula, is the current position of the i-th j-dimensional secretary bird; sx i,j represents the current position of the i-th j-dimensional secretary bird; R2 represents the array of dimension 1×Dim generated randomly from the normal distribution; sx random is the iterative random candidate solution position; K represents a random selection of integers 1 or 2; X COBLis the inverse solution generated by COBL; ub and lb are the upper and lower bounds of the search space respectively; rand is a random function that obeys a uniform distribution.

[0113] The strategy is executed NZ times until NZ> the second set value, namely Tt. In this embodiment, Tt=20 is taken. At this time, the optimal value is found to form a prediction model for the power battery SOH.

[0114] The improved vulture combination algorithm is used to optimize the modal decomposition number K and penalty factor α in the VMD algorithm. The fuzzy entropy of each modal component obtained by VMD decomposition of the SOH data set is set as the fitness function to find the optimal combination of [K, α] of the VMD algorithm.

[0115] The combined vulture algorithm is used to optimize the parameters C and g of the SVM, and then the data set processed by the VMD algorithm is trained. The root mean square error of the predicted and measured SOH of the selected battery data is used as the fitness value to obtain the hyperparameter combination that makes the SVM neural network model estimate the best, thereby obtaining the SOH intelligent prediction model of the power battery.

[0116] The number of charge and discharge times and charge and discharge parameters are collected and accumulated in real time, and put into the prediction model to obtain the SOH value at that time, thereby obtaining a prediction method and system for the SOH of a power battery based on the vulture combination algorithm.

[0117] Embodiment 2

[0118] The purpose of this embodiment is to provide a prediction system for power battery SOH based on a vulture combination algorithm, including:

[0119] A data acquisition module is configured to acquire the number of charge and discharge times and charge and discharge parameters and construct a data set;

[0120] A prediction model building module is configured to use a vulture combination algorithm to optimize the parameters of the variational mode decomposition algorithm and the parameters of the support vector machine based on the data set to build a SOH prediction model;

[0121] The prediction module is configured to obtain the number of charge and discharge times and charge and discharge parameters in real time, and obtain a predicted SOH value using a SOH prediction model based on the data obtained in real time;

[0122] The vulture combination algorithm uses vultures to perform spiral flight behavior to find the first optimal value, introduces the first optimal value into the prey consumption strategy of the secretary vulture algorithm to obtain the second optimal value, selects the optimal value between the first optimal value and the second optimal value, and iterates the above optimization process until the optimal solution that meets the requirements is obtained; when the optimization process falls into a local optimum, the escape strategy and reverse learning strategy of the secretary vulture algorithm are used to jump out of the local optimum and continue to find a better solution.

[0123] In further embodiments, there is also provided:

[0124] An electronic device includes a memory and a processor, and computer instructions stored in the memory and executed on the processor, wherein when the computer instructions are executed by the processor, the method described in Embodiment 1 is performed. For the sake of brevity, no further description is given here.

[0125] It should be understood that in this embodiment, the processor may be a central processing unit CPU, and the processor may also be other general-purpose processors, digital signal processors DSP, application-specific integrated circuits ASIC, off-the-shelf programmable gate arrays FPGA or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0126] The memory may include a read-only memory and a random access memory, and provide instructions and data to the processor. A portion of the memory may also include a non-volatile random access memory. For example, the memory may also store information about the device type.

[0127] A computer-readable storage medium is used to store computer instructions. When the computer instructions are executed by a processor, the method described in embodiment 1 is completed.

[0128] The method in the first embodiment can be directly embodied as a hardware processor, or a combination of hardware and software modules in the processor. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware. To avoid repetition, it will not be described in detail here.

[0129] A computer program product includes a computer program, and when the computer program is executed by a processor, the method described in the first embodiment is implemented.

[0130] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0131] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0132] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0133] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0134] 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 by those skilled in the art within the spirit and principle of the present invention without creative labor shall be included in the protection scope of the present invention.

Claims

1. A method for predicting SOH of a power battery based on a vulture combination algorithm, characterized in that: The following steps are involved: Obtain the number of charge and discharge times and charge and discharge parameters, and construct a data set; Based on the data set, the vulture combination algorithm is used to optimize the parameters of the variational mode decomposition algorithm and the parameters of the support vector machine to build a SOH prediction model; The charge and discharge times and charge and discharge parameters are acquired in real time, and the predicted SOH value is obtained by using the SOH prediction model based on the real-time acquired data; The vulture combination algorithm uses vultures to perform spiral flight behavior to find a first optimal value, introduces the first optimal value into the prey consumption strategy of the secretary vulture algorithm to obtain a second optimal value, selects the best value between the first optimal value and the second optimal value, and iterates the above optimization process until an optimal solution that meets the requirements is obtained; When the optimization process falls into a local optimum, the escape strategy and reverse learning strategy of the snake vulture algorithm are used to jump out of the local optimum and continue to look for a better solution.

2. The method for predicting the SOH of a power battery based on the vulture combination algorithm according to claim 1, characterized in that: The process of obtaining the number of charge and discharge times and charge and discharge parameters includes charging and discharging at a set temperature with a predetermined current and voltage as a charge / discharge test cycle, which is repeated continuously until the battery capacity is reduced to a set value, thereby obtaining a data set of SOH, the number of charge and discharge times and the charge and discharge parameters.

3. The method for predicting the SOH of a power battery based on the vulture combination algorithm according to claim 1, characterized in that: The process of using the vulture to perform spiral flight behavior to find the first optimal value includes: performing the spiral flight behavior through the vulture algorithm to find the first optimal value, denoted as x best , the formula is as follows: in, is the position of the ith individual at time t+1, is the position of the i-th individual at time t, and t is the number of iterations; represents the optimal individual at time t, r5 and r6 are both random numbers between 0 and 1.

4. The method for predicting the SOH of a power battery based on the vulture combination algorithm according to claim 3, characterized in that: The process of introducing the first optimal value into the prey consumption strategy of the secretary vulture algorithm includes: best Introduced into the process of consuming prey by the secretary vulture algorithm, the formula is as follows: RB=randn(1,Dim) Where RB is Brownian motion; randn(1,Dim) represents an array of dimension 1×Dim randomly generated from a standard normal distribution; is the current position of the i-th j-dimensional secretary bird; The current optimal position of the secretary bird; represents the current position of the i-th j-dimensional secretary bird at time t; The second optimal value is found through the prey consumption strategy of the secretary vulture algorithm, denoted as x' best .

5. The method for predicting the SOH of a power battery based on the vulture combination algorithm according to claim 1, characterized in that: The above optimization process until the optimal solution that meets the requirements is obtained includes: taking the first optimal value x best and the second optimal value x' best The optimal value of the two judge Whether the consecutive times that the value is less than the set value exceeds the predetermined times, if so, it falls into the local optimum, if not, it returns to the optimization process until it falls into the local optimum.

6. The method for predicting the SOH of a power battery based on a vulture combination algorithm according to claim 1, characterized in that: When the optimization process falls into a local optimum, the escape strategy and reverse learning strategy of the Snake Vulture algorithm are adopted. The process of jumping out of the local optimum includes: executing the escape strategy of the Snake Vulture algorithm, the formula is as follows: The obtained results are introduced into the reverse learning strategy, and the formula is as follows: K = round(1+rand(1,1)) in, is the current position of the i-th j-dimensional secretary bird; sx i,j represents the current position of the i-th j-dimensional secretary bird; R2 represents the array of dimension 1×Dim generated randomly from the normal distribution; sx random is the iterative random candidate solution position; K represents a random selection of integers 1 or 2; X COBL is the inverse solution generated by COBL; ub and lb are the upper and lower bounds of the search space respectively; rand is a random function that obeys uniform distribution; Execute the above strategy a set number of times to find the optimal solution.

7. The method for predicting the SOH of a power battery based on a vulture combination algorithm according to claim 1, characterized in that: The process of using the vulture combination algorithm to optimize the parameters of the variational mode decomposition algorithm includes using the vulture combination algorithm to optimize the number of modal decompositions K and the penalty factor α of the variational mode decomposition algorithm, using the fuzzy entropy of each modal component obtained by the variational mode decomposition algorithm of the data set as the fitness function, and finding the optimal combination of [K, α] of the variational mode decomposition algorithm.

8. The method for predicting the SOH of a power battery based on a vulture combination algorithm according to claim 1, characterized in that: The process of optimizing the parameters of the support vector machine using the vulture combination algorithm includes optimizing the parameters C and g of the support vector machine using the vulture combination algorithm, and then training with the data set decomposed by the variational mode decomposition algorithm. The root mean square error of the predicted and measured SOH is used as the fitness value to obtain the hyperparameter combination that makes the support vector machine estimation effect the best, forming a SOH prediction model.

9. A prediction system for power battery SOH based on vulture combination algorithm, characterized in that: include: A data acquisition module is configured to acquire the number of charge and discharge times and charge and discharge parameters and construct a data set; A prediction model building module is configured to use a vulture combination algorithm to optimize the parameters of the variational mode decomposition algorithm and the parameters of the support vector machine based on the data set to build a SOH prediction model; The prediction module is configured to obtain the number of charge and discharge times and charge and discharge parameters in real time, and obtain a predicted SOH value using a SOH prediction model based on the data obtained in real time; The vulture combination algorithm uses vultures to perform spiral flight behavior to find the first optimal value, introduces the first optimal value into the prey consumption strategy of the secretary vulture algorithm to obtain the second optimal value, selects the optimal value between the first optimal value and the second optimal value, and iterates the above optimization process until the optimal solution that meets the requirements is obtained; when the optimization process falls into a local optimum, the escape strategy and reverse learning strategy of the secretary vulture algorithm are used to jump out of the local optimum and continue to find a better solution.

10. An electronic device, characterized in that: The method comprises a memory and a processor, and computer instructions stored in the memory and executed on the processor, wherein when the computer instructions are executed by the processor, the steps in the method according to any one of claims 1 to 8 are completed.

Images