Charging and discharging control method and system for mobile power supply

Abstract

The invention discloses a mobile power supply charging and discharging control method and system, and relates to the technical field of data processing, and the method comprises the steps: obtaining the temperature change information and pressure change information of a target mobile power supply; performing position marking on the battery cells of the target mobile power supply, collecting historical operation data of N battery cells, obtaining N operation data sets, and performing gradient descent traversal in combination with the position marks to obtain a target battery cell; and taking the operation data set of the target battery cell as a target operation data set, combining the temperature change information and the pressure change information, inputting the target operation data set into the charge and discharge control model for iterative optimization, obtaining an optimal charge and discharge control scheme, and performing charge and discharge control on the target mobile power supply. The technical problem that the service life of the power supply is shortened due to unbalanced charge and discharge control of the mobile power supply in the prior art is solved, and the technical effect of prolonging the service life of the mobile power supply by performing charge and discharge balance control on the mobile power supply is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a mobile power supply charging and discharging control method and system. Background Art

[0002] Currently, most mobile power supplies use lithium batteries. However, during the production process of lithium-powered batteries, there are subtle differences between individual lithium-powered batteries, such as differences in capacity, internal resistance, self-discharge rate, and charge and discharge efficiency. Therefore, it is impossible to ensure that each lithium-powered battery remains in the same state during normal use. There are cases of overcharge and overdischarge. If balanced control is not performed, as the charge and discharge cycles increase, the voltage of each lithium-powered battery will gradually diverge, which will shorten the service life of the mobile power supply. Summary of the invention

[0003] The present application provides a mobile power supply charge and discharge control method and system, which are used to solve the technical problem in the prior art that the life of the power supply is shortened due to unbalanced charge and discharge control of the mobile power supply.

[0004] In a first aspect of the present application, a mobile power supply charge and discharge control method is provided, the method comprising: obtaining operating environment information of a target mobile power supply within a preset time window, wherein the operating environment information comprises temperature change information and pressure change information; marking the position of the cells in the power supply battery based on the factory data of the target mobile power supply, and obtaining N cells with position marks; collecting historical operating data of the N cells, and obtaining N operating data sets, wherein each operating data set comprises a single cell capacity, a self-discharge rate, and a charge and discharge efficiency; performing gradient descent traversal based on the N operating data sets and the position marks, and obtaining a target cell; obtaining the operating data set of the target cell as a target operating data set; inputting the target operating data set, the temperature change information, and the pressure change information into a charge and discharge control model for iterative optimization, and obtaining an optimal charge and discharge control scheme;

[0005] The target mobile power source is charged and discharged according to the optimal charge and discharge control scheme.

[0006] In a second aspect of the present application, a mobile power supply charge and discharge control system is provided, the system comprising: an operating environment information acquisition module, the operating environment information acquisition module is used to acquire the operating environment information of the target mobile power supply within a preset time window, wherein the operating environment information includes temperature change information and pressure change information; a battery cell position marking module, the battery cell position marking module is used to mark the position of the battery cells in the power supply battery based on the factory data of the target mobile power supply, and obtain N battery cells with position marks; a battery cell operation data set acquisition module, the battery cell operation data set acquisition module is used to collect the historical operation data of the N battery cells, and obtain N operation data sets, wherein each operation data set includes a single cell capacity, self-discharge rate and charge and discharge efficiency; a target battery cell acquisition module, the target battery cell acquisition module is used to perform gradient descent traversal based on the N operation data sets and the position mark to obtain the target battery cell; a target operation data set acquisition module, the target operation data set acquisition module is used to obtain the operation data set of the target battery cell as the target operation data set; an optimal charge and discharge control scheme acquisition module, the optimal charge and discharge control scheme acquisition analysis module is used to input the target operation data set, the temperature change information and the pressure change information into the charge and discharge control model for iterative optimization to obtain the optimal charge and discharge control scheme; a charge and discharge control module, the charge and discharge control module is used to control the charge and discharge of the target mobile power supply according to the optimal charge and discharge control scheme.

[0007] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0008] The present application provides a mobile power supply charge and discharge control method, which relates to the field of data processing technology. By acquiring temperature change information and pressure change information of a target mobile power supply, the position of the battery cell of the target mobile power supply is marked, historical operation data of N battery cells are collected, and N operation data sets are obtained. Gradient descent traversal is performed in combination with the position mark to obtain the target battery cell. The operation data set of the target battery cell is then taken as the target operation data set, and the temperature change information and the pressure change information are input into a charge and discharge control model for iterative optimization to obtain an optimal charge and discharge control scheme. The target mobile power supply is charged and discharged according to the optimal charge and discharge control scheme, which solves the technical problem of the reduced power supply life due to unbalanced charge and discharge control of the mobile power supply in the prior art, and realizes the technical effect of performing charge and discharge balance control according to the data corresponding to the most stable battery cell among multiple battery cells of the mobile power supply to avoid overcharging and over-discharging of the power supply, thereby extending the service life of the mobile power supply. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0010] Figure 1 A schematic flow chart of a mobile power supply charging and discharging control method provided in an embodiment of the present application;

[0011] Figure 2 A schematic diagram of a process for obtaining a target battery cell in a mobile power supply charge and discharge control method provided in an embodiment of the present application;

[0012] Figure 3 A schematic diagram of a flow chart for obtaining an optimal charging and discharging control scheme in a mobile power supply charging and discharging control method provided in an embodiment of the present application;

[0013] Figure 4 A schematic diagram of the structure of a mobile power supply charging and discharging control system provided in an embodiment of the present application.

[0014] Explanation of the reference numerals: operating environment information acquisition module 11 , battery cell position marking module 12 , battery cell operation data set acquisition module 13 , target battery cell acquisition module 14 , target operation data set acquisition module 15 , optimal charge and discharge control scheme acquisition module 16 , charge and discharge control module 17 . DETAILED DESCRIPTION

[0015] The present application provides a mobile power supply charge and discharge control method, which is used to solve the technical problem in the prior art that the life of the mobile power supply is shortened due to unbalanced charge and discharge control of the mobile power supply.

[0016] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0017] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices.

[0018] Embodiment 1

[0019] like Figure 1 As shown, the present application provides a mobile power supply charging and discharging control method, the method comprising:

[0020] S100: Acquire operating environment information of a target mobile power source within a preset time window, wherein the operating environment information includes temperature change information and pressure change information;

[0021] Specifically, the operating environment information of the target mobile power supply within a preset time window is obtained, and the preset time window refers to a data monitoring window used to collect the operating environment information of the target power supply. The monitored operating environment information has a corresponding time mark, and the operating environment information includes temperature change information and pressure change information, which can reflect the temperature and pressure changes of the working environment of the target mobile power supply over a period of time. Because the temperature and pressure of the working environment will affect the charging and discharging performance of the mobile power supply, the temperature change information and pressure change information can be used as reference data for subsequent charging and discharging control.

[0022] S200: Marking the positions of the cells in the power supply battery based on the factory data of the target mobile power supply to obtain N cells with position marks;

[0023] Specifically, according to the factory data of the target mobile power supply, the position distribution of the cells in the mobile power supply battery is obtained, the position of each cell is determined, and the position is marked to obtain N cells with position marks. Because in the mobile power supply, the distance between the cell and the heat dissipation port will cause the cell to be in different temperature fields, and the cell temperature being too high or too low will affect the operation of the cell. Therefore, the cell is affected to different degrees in different temperature fields, so it is necessary to correct the cell operation data according to the position of the cell when the gradient is subsequently descended.

[0024] S300: Collecting historical operation data of the N battery cells to obtain N operation data sets, wherein each operation data set includes a single cell capacity, a self-discharge rate, and a charge and discharge efficiency;

[0025] Specifically, the historical operation data of the N battery cells in the past period of time (which can be one month, three months, etc., and the specific time can be adaptively adjusted according to the actual situation) are collected respectively to obtain N operation data sets of the N battery cells, each of which includes single cell capacity, self-discharge rate and charge-discharge efficiency. The single cell capacity refers to the amount of electric energy that can be stored in a single battery cell. The self-discharge rate refers to the rate of decrease in the capacity of the battery cell during storage, that is, the speed at which the battery loses capacity due to self-discharge when there is no load, which can represent the characteristics of the capacity change of the mobile power supply after being shelved. The charge-discharge efficiency refers to the ratio of the energy consumed by the battery cell during the charging and discharging process to the input energy. The higher the charge-discharge efficiency, the smaller the loss of the battery cell and the higher the energy utilization rate. The N operation data sets can be used as basic data for subsequent battery cell optimization.

[0026] S400: performing gradient descent traversal based on the N operation data sets and the position markers to obtain a target battery cell;

[0027] Specifically, a gradient descent algorithm is used to traverse the N operating data sets and the position markers to optimize the battery cells, and the most stable battery cell among the multiple battery cells of the target mobile power source is obtained as the target battery cell. The gradient descent algorithm is a method for finding a minimized loss function, which uses gradient information and continuously iterates to adjust parameters to find a suitable target value. Charging and discharging control is performed according to the data corresponding to the target battery cell, which can avoid overcharging and overdischarging of the mobile power source and extend the service life of the mobile power source.

[0028] Further, such as Figure 2 As shown, step S400 of the embodiment of the present application also includes:

[0029] S410: traversing the N running data sets to perform mean processing to obtain N running mean sets;

[0030] S420: performing difference calculations on the N operating data sets and the N operating mean value sets respectively to obtain N operating deviation data sets;

[0031] S430: respectively comparing the N operation deviation data sets with the N operation data sets to determine deviations, and obtaining N operation deviation sets, wherein each operation deviation set includes a monomer capacity deviation, a self-discharge rate deviation, and a charge-discharge efficiency deviation.

[0032] Specifically, all the operating data in the N operating data sets are traversed, and the average values ​​of the monomer capacity, self-discharge rate and charge and discharge efficiency in the N operating data sets are calculated respectively to obtain N operating mean value sets, and the difference between all the operating data in the N operating data sets and the corresponding means in the N operating mean value sets is calculated respectively to obtain the deviation data between each operating data and the corresponding average value, and form N operating deviation data sets, wherein the deviation data has positive and negative values, and a negative value indicates that the operating data is lower than the average level, and a positive value indicates that the operating data is higher than the average level.

[0033] Furthermore, the deviation data in the N operation deviation data sets are respectively compared with the corresponding operation data in the N operation data sets, and the ratio is used as the deviation degree to obtain N operation deviation degree sets corresponding to the N battery cells, wherein each operation deviation degree set includes the single cell capacity deviation degree, self-discharge rate deviation degree and charge-discharge efficiency deviation degree of the battery cell. The N operation deviation degree sets can provide processed analysis data for subsequent gradient descent.

[0034] Furthermore, step S400 in the embodiment of the present application further includes:

[0035] S440: Randomly select a running deviation set from the N running deviation sets as a gradient descent initial point;

[0036] S450: using the gradient descent initial point, performing random iteration in the N running deviation degree sets according to the first step length, obtaining a first descent point, and calculating a first comprehensive deviation degree according to the corresponding first running deviation degree set and the position mark of the first descent point, and using the first comprehensive deviation degree as a first descent gradient;

[0037] S460: Determine whether the first descent gradient satisfies a preset descent gradient range. If so, determine that the first descent point is not the stage optimal point, and perform random iterations with the first descent gradient according to the first step length to obtain a second internal point.

[0038] Specifically, a running deviation set is randomly selected from the N running deviation sets as the initial point of gradient descent, that is, a battery cell is randomly selected as the starting point for battery cell optimization, and the initial point of gradient descent is randomly iterated in the N running deviation sets according to the first step length, and the first step length refers to the moving distance of the battery cell each time. According to the first step length, the current battery cell is moved a certain distance, and the battery cell closest to the current battery cell after the movement is taken as the first descent point, and the first comprehensive deviation is calculated according to the first running deviation set corresponding to the first descent point and the position mark of the first descent point, that is, the average of the running deviations of the battery cell at the initial point of gradient descent and the battery cell at the first descent point is calculated as the first comprehensive deviation, and the first comprehensive deviation is used as the first descent gradient.

[0039] Furthermore, it is determined whether the first descent gradient is greater than a preset descent gradient range, which is set by professionals according to the working principle of the battery cell. If it is greater than, it means that the operating deviation of the battery cell at the first descent point is too large, and the battery cell operation is not stable enough. It can be determined that the first descent point is not the optimal point of the stage. Then, the first descent gradient is randomly iterated and moved according to the first step to obtain a second internal point. The internal point is any one of the operating deviation sets, and so on. The iterative optimization is continued according to the second internal point until the battery cell with the smallest operating deviation is found as the target battery cell.

[0040] Furthermore, step S400 in the embodiment of the present application further includes:

[0041] S470: If not satisfied, determining the first descent point as the stage optimal point, performing random iteration with the first descent gradient according to a second step length to obtain the second internal point, wherein the second step length is smaller than the first step length;

[0042] S480: After multiple random iterations, until a preset number of iterations is met, a Pth internal point is obtained;

[0043] S490: The battery cell corresponding to the P-th internal point is used as the target battery cell.

[0044] Specifically, if it is not satisfied, that is, the first descent gradient is less than or equal to the preset descent gradient range, then it means that the operation deviation of the battery cell at the first descent point is relatively small, and the battery cell with the most stable operation may be nearby, and it is necessary to search with a smaller step size. Therefore, the first descent gradient is randomly iterated according to the second step size, and the second step size is smaller than the first step size to obtain the second internal point. Similarly, the comprehensive operation deviation is calculated based on the second internal point and compared with the preset descent gradient range, and multiple random iterations are continued until the number of iterations reaches the preset number of iterations to obtain the Pth internal point. The Pth internal point is the battery cell with the smallest operation deviation, and the battery cell corresponding to the Pth internal point is used as the target battery cell.

[0045] S500: Acquire the operating data set of the target battery cell as a target operating data set;

[0046] Specifically, an operating data set of the target battery cell is obtained, including the single cell capacity, self-discharge rate and charge and discharge efficiency of the target battery cell, and this is used as a target operating data set, which can be used as a reference for the operating data of all battery cells of the target power supply to correct the operating data of all battery cells.

[0047] S600: inputting the target operation data set, the temperature change information and the pressure change information into a charge and discharge control model for iterative optimization to obtain an optimal charge and discharge control solution;

[0048] Further, such as Figure 3 As shown, step S600 in the embodiment of the present application also includes:

[0049] S610: Acquire multiple sample target operation data sets, multiple sample temperature change information, multiple pressure change information, and multiple sample charge and discharge control schemes as construction data;

[0050] S620: Performing supervised training on a framework constructed based on a feedforward neural network using the constructed data until the output reaches convergence, thereby obtaining an output branch of a control scheme for the charge and discharge control model;

[0051] S630: After inputting the target operation data set, the temperature change information, and the pressure change information into a control scheme output branch in a charge and discharge control model, a target charge and discharge control scheme set is obtained.

[0052] Specifically, based on big data, the charging and discharging control data of multiple mobile power sources of the same type are obtained as sample data, including multiple sample target operation data sets, multiple sample temperature change information, multiple pressure change information, and multiple sample charging and discharging control schemes, which are used as the construction data of the control scheme output branch of the charging and discharging control model. The framework of the control scheme output branch is constructed in combination with a feedforward neural network, and the construction data is randomly divided into a training data set, a verification data set, and a test data set. The control scheme output branch is trained, verified, and tested based on the training data set, the verification data set, and the test data set until the model output converges and meets the preset accuracy requirements, so as to obtain the control scheme output branch of the charging and discharging control model.

[0053] Furthermore, after the target operation data set, the temperature change information and the pressure change information are respectively input into the control scheme output branch in the charge and discharge control model, the control scheme output branch outputs multiple target charge and discharge control schemes to form a target charge and discharge control scheme set.

[0054] Furthermore, step S600 in the embodiment of the present application further includes:

[0055] S640: Randomly selecting a target charge and discharge control scheme from the target charge and discharge control scheme set without replacement as a first target charge and discharge control scheme;

[0056] S650: Calculate the fitness of the first target charge and discharge control scheme to obtain a first target fitness;

[0057] S660: randomly selecting a target charge and discharge control scheme from the target charge and discharge control scheme set without replacement as a second target charge and discharge control scheme;

[0058] S670: Calculate the fitness of the second target charge and discharge control scheme to obtain the second target fitness, and determine whether the second target fitness is greater than the first target fitness. If so, use the second target charge and discharge control scheme as the optimal control scheme for the stage. If so, accept the second target charge and discharge control scheme as the optimal control scheme for the stage according to a certain probability.

[0059] S680: After multiple iterations of optimization, when the first number of iterations is reached, the optimal control solution for the stage obtained by iteration is used as the optimal charge and discharge control solution.

[0060] Specifically, a target charge and discharge control scheme is randomly selected from the target charge and discharge control scheme set without replacement as the first target charge and discharge control scheme, and the fitness of the first target charge and discharge control scheme is calculated by combining the charge and discharge control data of multiple historical charge and discharge control schemes with the algorithm mathematical model, and this is used as the first target fitness. Further, a target charge and discharge control scheme is randomly selected from the target charge and discharge control scheme set without replacement as the second target charge and discharge control scheme, and the fitness of the second target charge and discharge control scheme is calculated as the second target fitness.

[0061] Furthermore, the second target fitness is compared with the first target fitness to determine whether the second target fitness is greater than the first target fitness. If so, the second target charge and discharge control scheme is used as the optimal control scheme for the stage. If so, the second target charge and discharge control scheme is accepted as the optimal control scheme for the stage with a certain probability to avoid falling into a local optimal solution. Exemplarily, an allowable value is set. When the allowable value is greater than 1, the second target charge and discharge control scheme can be used as the optimal control scheme for the stage. The allowable value decreases with the increase of the number of iterations and eventually returns to 0.

[0062] By analogy, all schemes in the target charge and discharge control scheme set are iterated and optimized according to fitness, until the number of iterations reaches the first number of iterations, then the optimization is stopped and the optimal control scheme of the current stage is used as the optimal charge and discharge control scheme. The first number of iterations is set by professionals according to computing power and optimization cost.

[0063] Furthermore, step S650 of the embodiment of the present application further includes:

[0064] S651: Obtaining the control cost, control time, and control frequency of the first target charge and discharge control scheme;

[0065] S652: Input the control cost, control time and control frequency into the three-dimensional coordinate system for fitness calculation, obtain k adjacent historical coordinate points, and use the fitness mean corresponding to the k historical coordinate points as the first target fitness of the first target charge and discharge control scheme, where k is an integer greater than or equal to 3.

[0066] Specifically, based on big data, the control cost, control time and control frequency data of the first target charge and discharge control scheme are extracted, and the control cost, control time and control frequency are input into the three-dimensional coordinate system for fitness calculation to form a control cost-control time-control frequency coordinate point. The three-dimensional coordinate system for fitness calculation contains multiple historical coordinate points. The smaller the distance between the coordinate point and the historical coordinate point, the greater the similarity of the fitness. Therefore, k historical coordinate points adjacent to the coordinate point are extracted, and the fitness mean corresponding to the k historical coordinate points is used as the first target fitness of the first target charge and discharge control scheme. k is an integer greater than or equal to 3, which means that the number of extracted historical coordinate points is at least 3.

[0067] Furthermore, step S652 of the embodiment of the present application further includes:

[0068] S652-1: respectively collecting control costs, control times, and control frequencies of multiple historical charge and discharge control schemes, and fitness of multiple historical charge and discharge control schemes, to obtain multiple historical control costs, multiple historical control times, and multiple historical control frequencies;

[0069] S652-2: constructing a framework of the fitness calculation three-dimensional coordinate system with control cost as the x-axis, control time as the y-axis, and control frequency as the z-axis;

[0070] S652-3: Input multiple historical control costs, multiple historical control times, and multiple historical control frequencies into the fitness calculation three-dimensional coordinate system to obtain multiple historical coordinate points, and mark the multiple historical coordinate points according to the fitness of multiple historical charge and discharge control schemes.

[0071] Specifically, based on big data, the control cost, control time and control frequency of multiple historical charge and discharge control schemes, as well as the fitness of multiple historical charge and discharge control schemes are collected respectively, so as to obtain multiple historical control costs, multiple historical control times and multiple historical control frequencies as construction data, and use the control cost as the x-axis, the control time as the y-axis, and the control frequency as the z-axis to construct the framework of the fitness calculation three-dimensional coordinate system, and then input the multiple historical control costs, multiple historical control times and multiple historical control frequencies into the fitness calculation three-dimensional coordinate system to form multiple historical coordinate points, and use the fitness of multiple historical charge and discharge control schemes to mark the corresponding multiple historical coordinate points, and finally use the coordinate system containing multiple marked historical coordinate points as the fitness calculation three-dimensional coordinate system.

[0072] S700: Controlling the charging and discharging of the target mobile power source according to the optimal charging and discharging control scheme.

[0073] Specifically, according to the optimal charge and discharge control scheme, the charging current and voltage, the discharging current and voltage, the charge and discharge time, the ambient temperature and the number of cycles of the target mobile power source are controlled to avoid overcharging and overdischarging and extend the service life of the mobile power source.

[0074] In summary, the embodiments of the present application have at least the following technical effects:

[0075] The present application obtains the temperature change information and pressure change information of the target mobile power supply, marks the position of the battery cells of the target mobile power supply, collects the historical operation data of N battery cells, obtains N operation data sets, performs gradient descent traversal in combination with the position marks, obtains the target battery cell, and then collects the operation data set of the target battery cell as the target operation data set, combines the temperature change information and the pressure change information into the charge and discharge control model for iterative optimization, obtains the optimal charge and discharge control scheme, and controls the charge and discharge of the target mobile power supply according to the optimal charge and discharge control scheme.

[0076] The technical effect of performing charge and discharge balance control according to data corresponding to the most stable battery cell among multiple battery cells of the mobile power supply is achieved to avoid overcharging and overdischarging of the power supply, thereby extending the service life of the mobile power supply.

[0077] Embodiment 2

[0078] Based on the same inventive concept as the mobile power supply charging and discharging control method in the above-mentioned embodiment, Figure 4 As shown, the present application provides a mobile power supply charging and discharging control system, and the system and method embodiments in the present application are based on the same inventive concept. The system includes:

[0079] An operating environment information acquisition module 11, the operating environment information acquisition module 11 is used to obtain the operating environment information of the target mobile power supply within a preset time window, wherein the operating environment information includes temperature change information and pressure change information;

[0080] A cell position marking module 12, the cell position marking module 12 is used to mark the positions of the cells in the power supply battery based on the factory data of the target mobile power supply, and obtain N cells with position marks;

[0081] A cell operation data set acquisition module 13, wherein the cell operation data set acquisition module 13 is used to collect historical operation data of the N cells to obtain N operation data sets, wherein each operation data set includes a single cell capacity, a self-discharge rate, and a charge and discharge efficiency;

[0082] A target cell acquisition module 14, wherein the target cell acquisition module 14 is used to perform a gradient descent traversal based on the N operation data sets and the position markers to obtain a target cell;

[0083] A target operation data set acquisition module 15, wherein the target operation data set acquisition module 15 is used to acquire the operation data set of the target battery cell as the target operation data set;

[0084] The optimal charge and discharge control scheme acquisition module 16 is used to input the target operation data set, the temperature change information and the pressure change information into the charge and discharge control model for iterative optimization to obtain the optimal charge and discharge control scheme;

[0085] The charge and discharge control module 17 is used to control the charge and discharge of the target mobile power source according to the optimal charge and discharge control scheme.

[0086] Furthermore, the target cell acquisition module 14 is further configured to perform the following steps:

[0087] Traversing the N running data sets to perform mean processing to obtain N running mean sets;

[0088] Performing difference calculations on the N operating data sets and the N operating mean value sets respectively to obtain N operating deviation data sets;

[0089] The N operation deviation data sets are respectively compared with the N operation data sets to determine the deviation degree, and N operation deviation degree sets are obtained, wherein each operation deviation degree set includes a monomer capacity deviation degree, a self-discharge rate deviation degree and a charge and discharge efficiency deviation degree.

[0090] Furthermore, the target cell acquisition module 14 is further configured to perform the following steps:

[0091] Randomly select a running deviation set from the N running deviation sets as the initial point of gradient descent;

[0092] Using the gradient descent initial point, randomly iterate in the N running deviation degree sets according to the first step length to obtain a first descent point, and calculate a first comprehensive deviation degree according to the corresponding first running deviation degree set and the position mark of the first descent point, and use the first comprehensive deviation degree as the first descent gradient;

[0093] Determine whether the first descent gradient satisfies a preset descent gradient range. If so, determine that the first descent point is not the stage optimal point, and perform random iterations with the first descent gradient according to the first step length to obtain a second internal point.

[0094] Furthermore, the target cell acquisition module 14 is further configured to perform the following steps:

[0095] If not, the first descent point is determined to be the stage optimal point, and the first descent gradient is randomly iterated according to the second step length to obtain the second internal point, wherein the second step length is smaller than the first step length;

[0096] After multiple random iterations, until the preset number of iterations is met, the Pth internal point is obtained;

[0097] The battery cell corresponding to the P-th internal point is taken as the target battery cell.

[0098] Furthermore, the optimal charge and discharge control scheme obtaining module 16 is further used to perform the following steps:

[0099] Acquire multiple sample target operation data sets, multiple sample temperature change information, multiple pressure change information, and multiple sample charge and discharge control schemes as construction data;

[0100] Using the constructed data to perform supervised training on a framework constructed based on a feedforward neural network until the output reaches convergence, thereby obtaining an output branch of the control scheme of the charge and discharge control model;

[0101] After the target operation data set, the temperature change information and the pressure change information are input into a control scheme output branch in a charge and discharge control model, a target charge and discharge control scheme set is obtained.

[0102] Furthermore, the optimal charge and discharge control scheme obtaining module 16 is further used to perform the following steps:

[0103] Randomly selecting a target charge and discharge control scheme from the target charge and discharge control scheme set without replacement as a first target charge and discharge control scheme;

[0104] Calculating the fitness of the first target charge and discharge control scheme to obtain a first target fitness;

[0105] randomly selecting a target charge and discharge control scheme from the target charge and discharge control scheme set without replacement as a second target charge and discharge control scheme;

[0106] Calculate the fitness of the second target charge and discharge control scheme to obtain the second target fitness, and determine whether the second target fitness is greater than the first target fitness. If so, take the second target charge and discharge control scheme as the optimal control scheme for the stage. If so, accept the second target charge and discharge control scheme as the optimal control scheme for the stage according to a certain probability.

[0107] After multiple iterations of optimization, when the first number of iterations is reached, the optimal control solution for the stage obtained by iteration is used as the optimal charge and discharge control solution.

[0108] Furthermore, the optimal charge and discharge control scheme obtaining module 16 is further used to perform the following steps:

[0109] Obtaining the control cost, control time and control frequency of the first target charge and discharge control scheme;

[0110] The control cost, control time and control frequency are input into the three-dimensional coordinate system for fitness calculation to obtain k adjacent historical coordinate points, and the fitness mean corresponding to the k historical coordinate points is used as the first target fitness of the first target charge and discharge control scheme, where k is an integer greater than or equal to 3.

[0111] Furthermore, the optimal charge and discharge control scheme obtaining module 16 is further used to perform the following steps:

[0112] Collect control costs, control times, and control frequencies of multiple historical charge and discharge control schemes, and the fitness of multiple historical charge and discharge control schemes, respectively, to obtain multiple historical control costs, multiple historical control times, and multiple historical control frequencies;

[0113] The framework of the three-dimensional coordinate system for fitness calculation is constructed with control cost as the x-axis, control time as the y-axis, and control frequency as the z-axis;

[0114] Multiple historical control costs, multiple historical control times, and multiple historical control frequencies are input into a fitness calculation three-dimensional coordinate system to obtain multiple historical coordinate points, and the multiple historical coordinate points are marked according to the fitness of multiple historical charge and discharge control schemes.

[0115] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. Other embodiments are within the scope of the attached claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0116] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0117] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A mobile power supply charge and discharge control method, characterized in that: The method comprises: Acquire operating environment information of the target mobile power source within a preset time window, wherein the operating environment information includes temperature change information and pressure change information; Marking the positions of the cells in the power supply battery based on the factory data of the target mobile power supply to obtain N cells with position marks; Collecting historical operation data of the N battery cells to obtain N operation data sets, wherein each operation data set includes a single cell capacity, a self-discharge rate, and a charge and discharge efficiency; Performing gradient descent traversal based on the N operating data sets and the position markers to obtain a target battery cell; Acquire the operating data set of the target battery cell as a target operating data set; Inputting the target operation data set, the temperature change information and the pressure change information into a charge-discharge control model for iterative optimization to obtain an optimal charge-discharge control solution; The target mobile power source is charged and discharged according to the optimal charge and discharge control scheme.

2. The method according to claim 1, characterized in that The method of performing gradient descent traversal based on the N operating data sets and the position marks to obtain the target battery cell comprises: Traversing the N running data sets to perform mean processing to obtain N running mean sets; Performing difference calculations on the N operating data sets and the N operating mean value sets respectively to obtain N operating deviation data sets; The N operation deviation data sets are respectively compared with the N operation data sets to determine the deviation degree, and N operation deviation degree sets are obtained, wherein each operation deviation degree set includes a monomer capacity deviation degree, a self-discharge rate deviation degree and a charge and discharge efficiency deviation degree.

3. The method according to claim 2, characterized in that After obtaining N sets of running deviations, the method includes: Randomly select a running deviation set from the N running deviation sets as the initial point of gradient descent; Using the gradient descent initial point, randomly iterate in the N running deviation degree sets according to the first step length to obtain a first descent point, and calculate a first comprehensive deviation degree according to the corresponding first running deviation degree set and the position mark of the first descent point, and use the first comprehensive deviation degree as the first descent gradient; Determine whether the first descent gradient satisfies a preset descent gradient range. If so, determine that the first descent point is not the stage optimal point, and perform random iterations with the first descent gradient according to the first step length to obtain a second internal point.

4. The method according to claim 3, characterized in that The method comprises: If not, the first descent point is determined to be the stage optimal point, and the first descent gradient is randomly iterated according to the second step length to obtain the second internal point, wherein the second step length is smaller than the first step length; After multiple random iterations, until the preset number of iterations is met, the Pth internal point is obtained; The battery cell corresponding to the P-th internal point is taken as the target battery cell.

5. The method according to claim 1, characterized in that The method comprises: Acquire multiple sample target operation data sets, multiple sample temperature change information, multiple pressure change information, and multiple sample charge and discharge control schemes as construction data; Using the constructed data to perform supervised training on a framework constructed based on a feedforward neural network until the output reaches convergence, thereby obtaining an output branch of the control scheme of the charge and discharge control model; After the target operation data set, the temperature change information and the pressure change information are input into a control scheme output branch in a charge and discharge control model, a target charge and discharge control scheme set is obtained.

6. The method according to claim 5, characterized in that The method comprises: Randomly selecting a target charge and discharge control scheme from the target charge and discharge control scheme set without replacement as a first target charge and discharge control scheme; Calculating the fitness of the first target charge and discharge control scheme to obtain a first target fitness; randomly selecting a target charge and discharge control scheme from the target charge and discharge control scheme set without replacement as a second target charge and discharge control scheme; Calculate the fitness of the second target charge and discharge control scheme to obtain the second target fitness, and determine whether the second target fitness is greater than the first target fitness. If so, take the second target charge and discharge control scheme as the optimal control scheme for the stage. If so, accept the second target charge and discharge control scheme as the optimal control scheme for the stage according to a certain probability. After multiple iterations of optimization, when the first number of iterations is reached, the optimal control solution for the stage obtained by iteration is used as the optimal charge and discharge control solution.

7. The method according to claim 6, characterized in that The method comprises: Obtaining the control cost, control time and control frequency of the first target charge and discharge control scheme; The control cost, control time and control frequency are input into the three-dimensional coordinate system for fitness calculation to obtain k adjacent historical coordinate points, and the fitness mean corresponding to the k historical coordinate points is used as the first target fitness of the first target charge and discharge control scheme, where k is an integer greater than or equal to 3.

8. The method according to claim 7, characterized in that The method comprises: Collect control costs, control times, and control frequencies of multiple historical charge and discharge control schemes, and the fitness of multiple historical charge and discharge control schemes, respectively, to obtain multiple historical control costs, multiple historical control times, and multiple historical control frequencies; The framework of the three-dimensional coordinate system for fitness calculation is constructed with control cost as the x-axis, control time as the y-axis, and control frequency as the z-axis; Multiple historical control costs, multiple historical control times, and multiple historical control frequencies are input into a fitness calculation three-dimensional coordinate system to obtain multiple historical coordinate points, and the multiple historical coordinate points are marked according to the fitness of multiple historical charge and discharge control schemes.

9. A mobile power supply charging and discharging control system, characterized in that: The system comprises: An operating environment information acquisition module, the operating environment information acquisition module is used to obtain the operating environment information of the target mobile power supply within a preset time window, wherein the operating environment information includes temperature change information and pressure change information; A cell position marking module, the cell position marking module is used to mark the positions of the cells in the power battery based on the factory data of the target mobile power source, and obtain N cells with position marks; A cell operation data set acquisition module, the cell operation data set acquisition module is used to collect historical operation data of the N cells to obtain N operation data sets, wherein each operation data set includes a single cell capacity, a self-discharge rate, and a charge and discharge efficiency; A target cell acquisition module, the target cell acquisition module is used to perform a gradient descent traversal based on the N operation data sets and the position markers to obtain a target cell; A target operation data set acquisition module, wherein the target operation data set acquisition module is used to acquire the operation data set of the target battery cell as the target operation data set; An optimal charge and discharge control scheme acquisition module, wherein the optimal charge and discharge control scheme acquisition and analysis module is used to input the target operation data set, the temperature change information and the pressure change information into a charge and discharge control model for iterative optimization to obtain an optimal charge and discharge control scheme; A charge and discharge control module is used to control the charge and discharge of the target mobile power source according to the optimal charge and discharge control scheme.

Images