CN112018854B - Battery charging control method, device, terminal and storage medium - Google Patents
Battery charging control method, device, terminal and storage medium Download PDFInfo
- Publication number
- CN112018854B CN112018854B CN202010935594.0A CN202010935594A CN112018854B CN 112018854 B CN112018854 B CN 112018854B CN 202010935594 A CN202010935594 A CN 202010935594A CN 112018854 B CN112018854 B CN 112018854B
- Authority
- CN
- China
- Prior art keywords
- battery
- charging
- capacity
- actual capacity
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J7/00—Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries
- H02J7/007—Regulation of charging or discharging current or voltage
- H02J7/00712—Regulation of charging or discharging current or voltage the cycle being controlled or terminated in response to electric parameters
- H02J7/00714—Regulation of charging or discharging current or voltage the cycle being controlled or terminated in response to electric parameters in response to battery charging or discharging current
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/10—Energy storage using batteries
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
- Secondary Cells (AREA)
Abstract
The present disclosure provides a battery charging control method, device, terminal and storage medium, and relates to the technical field of batteries, wherein the method comprises: generating a training sample based on the battery charging historical parameters and the actual capacity value of the battery; training the constructed battery actual capacity prediction model by using a training sample; when the battery is charged, a trained actual battery capacity prediction model is used and prediction processing is carried out according to the current battery charging parameters to obtain a predicted value of the actual battery capacity; determining the battery capacity change speed according to the actual battery capacity predicted value; controlling a charging input current according to a battery capacity change speed by using a preset charging strategy; the method, the device, the terminal and the storage medium can automatically switch and adjust the charging current in the battery charging process, reduce the battery loss, achieve the effect of prolonging the service life of the battery, obtain the fastest charging speed under the condition of ensuring the optimal service life of the battery, and improve the customer experience.
Description
Technical Field
The present disclosure relates to the field of battery technologies, and in particular, to a battery charging control method and apparatus, a terminal, and a storage medium.
Background
The battery is used as a power source for electronic systems and electronic equipment, and the health state and the service life state of the battery directly influence the safe, reliable and efficient operation of the systems and the equipment. With the increase of the intelligence level and processing capability of electronic systems and devices, a series of problems caused by the battery life are gradually revealed. The problem of battery life refers to the gradual deterioration of physical and chemical structural properties of positive and negative active materials influencing the discharge capacity of the battery, the bonding strength of a viscous agent to a coating, the quality of a diaphragm and the like in the process of cyclic charge and discharge. The end of battery life, i.e., the degradation of the battery performance state to a certain threshold level, often results in a failure of the overall functionality of the system or device.
The battery is a dynamic, time-varying and nonlinear electrochemical system, the internal electrochemical mechanism of the battery is very complex, and the degradation of the performance state of the battery has certain uncertainty under the influence of various uncertain factors such as environmental temperature, load working conditions, oxidation, corrosion, vibration and the like. Irregular charging is one of the important factors that lead to a reduction in the life of the battery, and the actual capacity of the battery is an important parameter that characterizes the state of degradation of the battery. However, at present, parameters such as the actual capacity of the battery are usually difficult to directly measure in a charging state, and there is no technical solution in the prior art to control related operations in the battery charging process according to the change of the battery capacity so as to prolong the service life of the battery.
Disclosure of Invention
The present disclosure is proposed to solve the above technical problems. The embodiment of the disclosure provides a battery charging control method and device, a terminal and a storage medium.
According to a first aspect of an embodiment of the present disclosure, there is provided a battery charge control method including: acquiring a battery charging history parameter and a corresponding actual capacity value of a battery, and generating a training sample based on the battery charging history parameter and the actual capacity value of the battery; training the constructed battery actual capacity prediction model by using the training sample; when a battery is charged, acquiring current charging parameters of the battery, and performing prediction processing according to the current charging parameters of the battery by using a trained actual capacity prediction model of the battery to obtain a predicted value of the actual capacity of the battery; determining the battery capacity change speed according to the predicted value of the actual battery capacity; and controlling the charging input current according to the battery capacity change speed by using a preset charging strategy.
Optionally, the determining a battery capacity change speed according to the predicted battery actual capacity value includes: acquiring a battery actual capacity reference value, and calculating a difference value between the battery actual capacity predicted value and the battery actual capacity reference value; calculating the battery capacity change speed based on the difference. Wherein the battery actual capacity reference value includes: the actual capacity value of the battery after the last charging or the initial value of the actual capacity of the battery corresponding to the training sample.
Optionally, the battery charging history parameter and the battery charging current parameter include: single charge duration, single charge capacity, charge current, average battery temperature; the step of using the trained actual battery capacity prediction model and performing prediction processing according to the current battery charging parameter to obtain the actual battery capacity prediction value comprises the following steps: setting a parameter acquisition time interval; and periodically acquiring the current battery charging parameters based on the parameter acquisition time interval, inputting the current battery charging parameters into the actual battery capacity prediction model, and acquiring the predicted value of the actual battery capacity output by the actual battery capacity prediction model.
Optionally, the battery capacity change speed includes: the rate of decrease in battery capacity; the controlling of the charging input current according to the battery capacity variation speed using a preset charging strategy includes: determining a battery capacity drop speed threshold; periodically determining whether the battery capacity decrease rate is less than or equal to the battery capacity decrease rate threshold based on the parameter acquisition time interval; if yes, setting the charging input current as a preset maximum charging current; and if not, setting the charging input current as a preset current corresponding to the minimum actual capacity reduction speed of the battery.
Optionally, the determining the battery capacity decrease speed threshold comprises: acquiring an initial value of the actual capacity of the battery and a final value of the actual capacity of the battery corresponding to the training sample; and calculating the average descending speed of the actual capacity of the battery corresponding to the training sample according to the initial value of the actual capacity of the battery and the final value of the actual capacity of the battery, and taking the average descending speed of the actual capacity of the battery as the threshold value of the descending speed of the capacity of the battery.
Optionally, after the charging is completed, the single charging time, the single charging electric quantity, the charging current and the average temperature of the battery corresponding to the charging are recorded and stored.
Optionally, the battery actual capacity prediction model includes: a BP neural network model; the BP neural network model comprises an input layer, a hidden layer and an output layer; the training the constructed battery actual capacity prediction model by using the training samples comprises the following steps: taking the weight value and the threshold value of the BP neural network model as particles, and initializing; setting a fitness function according to the difference between the actual capacity training predicted value of the battery output by the output layer in the training process and the corresponding actual capacity true value of the battery; and optimizing the weight and the threshold value by adopting a particle swarm algorithm according to the fitness function in the training process to obtain a trained actual battery capacity prediction model.
Optionally, the number of the neurons of the input layer is four, and the four neurons correspond to the single charging time, the single charging capacity, the charging current and the average battery temperature respectively; the number of the neurons of the output layer is one, and the neurons correspond to the battery actual capacity predicted value and the battery actual capacity training predicted value; the number of neurons of the hidden layer is
Wherein h is the neuron number of the hidden layer, m is the neuron number of the input layer, n is the neuron number of the output layer, and k is an adjustment constant of 1-10.
Optionally, the excitation functions of the input layer and the output layer both adopt linear functions; the excitation function of the hidden layer adopts an s-type function;
the fitness function is:
wherein, the first and the second end of the pipe are connected with each other,
training a predicted value, y, for the battery actual capacity of the output node of the jth BP neural network model of the ith training sample j,i And n is the number of output neurons of the BP neural network model.
Optionally, determining a charging mode based on the received charging request signal; if the charging mode is the protection mode, acquiring the current charging parameters of the battery, using a preset charging strategy and controlling the charging input current according to the change speed of the battery capacity; and if the charging mode is the quick charging mode, setting the charging input current as a preset maximum charging current.
According to a second aspect of the embodiments of the present disclosure, there is provided a battery charge control device including: the training sample generating module is used for acquiring a battery charging history parameter and a corresponding actual battery capacity value and generating a training sample based on the battery charging history parameter and the actual battery capacity value; the prediction model training module is used for training the constructed battery actual capacity prediction model by using the training samples; the actual capacity prediction module is used for acquiring the current charging parameters of the battery when the battery is charged, and performing prediction processing according to the current charging parameters of the battery by using a trained actual capacity prediction model of the battery to acquire the predicted value of the actual capacity of the battery; the capacity change determining module is used for determining the battery capacity change speed according to the predicted value of the actual capacity of the battery; and the charging current control module is used for controlling the charging input current by using a preset charging strategy according to the change speed of the battery capacity.
According to a third aspect of the embodiments of the present disclosure, there is provided a battery charge control device including: a processor; a memory for storing the processor-executable instructions; the processor is used for reading the executable instructions from the memory and executing the instructions to realize the method.
According to a fourth aspect of embodiments of the present disclosure, there is provided a computer-readable storage medium storing a computer program for executing the above-mentioned method.
Based on the battery charging control method, the device, the terminal and the storage medium provided by the embodiment of the disclosure, the actual capacity of the battery is predicted in the charging process by constructing a battery actual capacity prediction model, and an optimal battery charging strategy is generated according to a judgment result of judging whether the actual capacity reduction speed of the battery is greater than the battery capacity reduction speed threshold; the charging current can be automatically switched and adjusted in the charging process of the battery, the battery loss is reduced, and the effect of prolonging the service life of the battery is achieved; the charging module of the battery can be controlled, the input current of charging is controlled, the performance degradation of the battery caused by charging non-specification is reduced, the fastest charging speed is obtained under the condition that the service life of the battery is ensured to be optimal, and the customer experience is improved; by adopting the particle swarm optimization to optimize the BP neural network, the problems that the BP neural network is low in learning efficiency, low in convergence speed and prone to falling into a local minimum value are solved.
The technical solution of the present disclosure is further described in detail by the accompanying drawings and examples.
Drawings
The above and other objects, features and advantages of the present disclosure will become more apparent by describing in more detail embodiments of the present disclosure with reference to the attached drawings. The accompanying drawings are included to provide a further understanding of the embodiments of the disclosure, and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the description serve to explain the principles of the disclosure and not to limit the disclosure. In the drawings, like reference numbers generally indicate like parts or steps.
FIG. 1 is a schematic flow chart diagram illustrating one embodiment of a battery charge control method of the present disclosure;
fig. 2 is a schematic flow chart of obtaining a predicted value of the actual capacity of the battery in an embodiment of the battery charging control method according to the present disclosure;
FIG. 3 is a flow chart illustrating the control of the charging current in one embodiment of the disclosed battery charging control method;
FIG. 4 is a schematic structural diagram of a BP neural network model according to the present disclosure;
FIG. 5 is a schematic flow chart diagram illustrating another embodiment of a battery charge control method according to the present disclosure;
FIG. 6 is a weight and threshold flow diagram of an optimized BP neural network model of the present disclosure;
FIG. 7 is a block diagram of one embodiment of a battery charge control device of the present disclosure;
FIG. 8 is a block diagram of a charging current control module in one embodiment of the battery charge control device of the present disclosure;
FIG. 9 is a block schematic diagram of another embodiment of a battery charge control apparatus of the present disclosure;
fig. 10 is a schematic structural diagram of a battery charge control apparatus according to still another embodiment of the present disclosure.
Detailed Description
Example embodiments according to the present disclosure will be described in detail below with reference to the accompanying drawings. It is to be understood that the described embodiments are merely a subset of the embodiments of the present disclosure and not all embodiments of the present disclosure, with the understanding that the present disclosure is not limited to the example embodiments described herein.
It should be noted that: the relative arrangement of parts and steps, numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present disclosure unless specifically stated otherwise.
It will be understood by those within the art that the terms "first", "second", etc. in the embodiments of the present disclosure are used only for distinguishing between different steps, devices or modules, etc., and do not denote any particular technical meaning or necessary logical order therebetween.
It is also understood that in embodiments of the present disclosure, "a plurality" may refer to two or more than two, and "at least one" may refer to one, two or more than two.
It is also to be understood that any reference to any component, data, or structure in the embodiments of the present disclosure may be generally understood as one or more, unless explicitly defined otherwise or indicated to the contrary hereinafter.
In addition, the term "and/or" in the present disclosure is only one kind of association relationship describing the associated object, and means that there may be three kinds of relationships, such as a and/or B, and may mean: a exists alone, A and B exist simultaneously, and B exists alone. In addition, the character "/" in the present disclosure generally indicates that the former and latter associated objects are in an "or" relationship.
It should also be understood that the description of the various embodiments of the present disclosure emphasizes the differences between the various embodiments, and the same or similar parts may be referred to each other, so that the descriptions thereof are omitted for brevity.
Meanwhile, it should be understood that the sizes of the respective portions shown in the drawings are not drawn in an actual proportional relationship for the convenience of description.
The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the disclosure, its application, or uses.
Techniques, methods, and apparatus known to one of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, it need not be discussed further in subsequent figures.
Embodiments of the present disclosure may be implemented in electronic devices such as terminal devices, computer systems, servers, etc., which are operational with numerous other general purpose or special purpose computing system environments or configurations. Examples of well known terminal devices, computing systems, environments, and/or configurations that may be suitable for use with an electronic device, such as a terminal device, computer system, or server, include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, hand-held or laptop devices, microprocessor-based systems, set top boxes, programmable consumer electronics, network pcs, minicomputer systems, mainframe computer systems, distributed cloud computing environments that include any of the above, and the like.
Electronic devices such as terminal devices, computer systems, servers, etc. may be described in the general context of computer system-executable instructions, such as program modules, being executed by a computer system. Generally, program modules may include routines, programs, objects, components, logic, data structures, etc. that perform particular tasks or implement particular abstract data types. The computer system/server may be implemented in a distributed cloud computing environment. In a distributed cloud computing environment, tasks may be performed by remote processing devices that are linked through a communications network. In a distributed cloud computing environment, program modules may be located in both local and remote computer system storage media including memory storage devices.
Exemplary method
Fig. 1 is a flowchart of an embodiment of a battery charging control method according to the present disclosure, where the method shown in fig. 1 includes the steps of: S101-S104. The following describes each step.
S101, acquiring a battery charging history parameter and a corresponding actual battery capacity value, and generating a training sample based on the battery charging history parameter and the actual battery capacity value.
In one embodiment, the battery may be a battery of an electronic product such as a mobile phone and a notebook computer, or a battery of an electric vehicle; the battery may be a lithium battery or the like. The battery charging history parameters comprise parameters such as single charging time, single charging electric quantity, charging current, battery average temperature and the like in the history charging process, and the corresponding actual capacity value of the battery can be the actual capacity value of the battery after the history charging. The existing methods and devices can be used for directly acquiring the single charging time length, the single charging electric quantity, the charging current, the average temperature of the battery and the actual capacity value of the battery.
The method comprises the steps of obtaining a plurality of battery charging historical parameters stored in a historical database in advance and corresponding actual capacity values of batteries, marking the battery charging historical parameters by using the actual capacity values of the batteries, and obtaining a plurality of training samples.
And S102, training the constructed battery actual capacity prediction model by using the training samples.
In one embodiment, the actual battery capacity prediction model may be CNN (convolutional Neural Network), DBN (deep belief Network), RNN (cyclic Neural Network), BP Neural Network (Back Propagation Neural Network), or the like. The training samples can be used for carrying out off-line training on the battery actual capacity prediction model to obtain the trained battery actual capacity prediction model.
S103, when the battery is charged, acquiring current charging parameters of the battery, and performing prediction processing according to the current charging parameters of the battery by using the trained actual capacity prediction model of the battery to obtain a predicted value of the actual capacity of the battery;
in one embodiment, when a battery is charged, acquiring current battery charging parameters, wherein the current battery charging parameters comprise current single charging time, single charging electric quantity, charging current, average battery temperature and other parameters of the battery; and inputting the current battery charging parameters into the actual battery capacity prediction model to obtain the predicted value of the actual battery capacity output by the actual battery capacity prediction model.
And S104, determining the battery capacity change speed according to the predicted value of the actual battery capacity.
And S105, controlling the charging input current according to the change speed of the battery capacity by using a preset charging strategy.
After each charging is completed, data such as a single charging time length, a single charging electric quantity, a charging current, a battery average temperature and a corresponding battery actual capacity value corresponding to the charging are recorded and stored in the historical database.
In one embodiment, the battery capacity change speed includes a battery capacity decrease speed or the like. When the battery is charged, the battery capacity reduction speed can be determined in real time or periodically according to the actual battery capacity predicted value, the charging input current is controlled by using a preset charging strategy according to the battery capacity reduction speed, and the charging input current, namely the current input into the battery, can be adjusted in the battery charging process; through the electric current that charges according to the actual capacity falling speed control of battery, can solve the problem that irregular frequency of charging leads to battery life to descend with length of time, extension battery life. The charging current input to the battery may be generated using a variety of existing devices.
Receiving a charging request signal input by a user, judging a charging mode based on the received charging request signal, and if the charging mode is a protection mode (power protection mode), acquiring current charging parameters of a battery, using a preset charging strategy and controlling charging input current according to the capacity change speed of the battery; and if the charging mode is the quick charging mode, setting the charging input current as the preset maximum charging current. The preset maximum charging current is a maximum current for charging the battery set according to the characteristics of the battery, etc.
In one embodiment, a battery actual capacity reference value is obtained, the battery actual capacity reference value comprising: the actual capacity value of the battery after the last charging or the initial value of the actual capacity of the battery corresponding to the training sample. And calculating a difference value between the predicted value of the actual capacity of the battery and the reference value of the actual capacity of the battery, and calculating the change speed of the capacity of the battery based on the difference value.
And acquiring a training sample with the earliest charging time, and acquiring a battery actual capacity value corresponding to the training sample, wherein the battery actual capacity value is an initial battery actual capacity value corresponding to the training sample. And acquiring the actual capacity value of the battery after the last charging is finished. And taking the actual capacity value of the battery after the last charging or the initial value of the actual capacity of the battery corresponding to the training sample as the reference value of the actual capacity of the battery.
The time interval between the training sample with the earliest charging time and the current charging time is obtained, and the unit may be days. And acquiring the time interval between the last charging time and the current charging time, wherein the unit can be day, and if the last charging time and the current charging time are on the same day, the time interval is 1 day. And calculating the difference value between the predicted value of the actual capacity of the battery and the reference value of the actual capacity of the battery, and taking the quotient of the difference value and the interval time as the change speed of the capacity of the battery.
For example, a training sample with the earliest charging time is obtained, and a battery actual capacity value a corresponding to the training sample is obtained, where the battery actual capacity value a is an initial battery actual capacity value corresponding to the training sample, that is, a battery actual capacity reference value. The time interval between the training sample with the earliest charging time and the current charging time is 200 days. And calculating ase:Sub>A difference B-A between the predicted value B of the actual battery capacity and the reference value A of the actual battery capacity, and taking the quotient of the difference B-A and the interval time of 200 days as the change speed of the battery capacity.
Fig. 2 is a schematic flowchart of a process of obtaining a predicted value of an actual capacity of a battery in an embodiment of a battery charging control method according to the present disclosure, where the method shown in fig. 2 includes the steps of: S201-S203. The following will explain each step.
S201, setting a parameter acquisition time interval. The parameter acquisition time interval may be set to 1 minute, 20 seconds, 1 second, etc.
And S202, periodically collecting the current battery charging parameters based on the parameter collection time interval.
And S203, inputting the current battery charging parameters into the actual battery capacity prediction model, and acquiring the predicted value of the actual battery capacity output by the actual battery capacity prediction model.
In one embodiment, the current battery charging parameters may be collected in real time, or may be collected based on a parameter collection time interval. For example, if the parameter collection time interval is 1 minute, periodically collecting current battery charging parameters at 1 minute intervals, where the current battery charging parameters include a single charging time h, a single charging capacity C, a charging current I, and a battery average temperature T, and when the current battery charging parameters are collected each time, accumulating the single charging time h and the single charging capacity C in each time interval.
And taking the single charging time h, the single charging electric quantity C, the charging current I and the battery average temperature T as input variables of the actual battery capacity prediction model, and taking the predicted value AC of the actual battery capacity as the output of the actual battery capacity prediction model.
In one embodiment, the charging strategy may be a variety of charging strategies. Fig. 3 is a schematic flowchart of controlling a charging current in an embodiment of the battery charging control method of the present disclosure, where the method shown in fig. 3 includes the steps of: S301-S304. The following describes each step.
S301, determining a battery capacity reduction speed threshold.
In one embodiment, an initial value of the actual capacity of the battery and a final value of the actual capacity of the battery corresponding to the training samples are obtained, an average descending speed of the actual capacity of the battery corresponding to the training samples is calculated according to the initial value of the actual capacity of the battery and the final value of the actual capacity of the battery, and the average descending speed of the actual capacity of the battery is used as a threshold value of the descending speed of the capacity of the battery.
And acquiring a training sample with the earliest charging time, and acquiring a battery actual capacity value corresponding to the training sample, wherein the battery actual capacity value is a battery actual capacity initial value corresponding to the training sample. And acquiring a training sample with the latest charging time, and acquiring a battery actual capacity value corresponding to the training sample, wherein the battery actual capacity value is a battery actual capacity final value corresponding to the training sample. The time interval between the training sample with the earliest charging time and the training sample with the latest charging time is obtained, and the unit can be day.
And calculating the difference between the initial value of the actual capacity of the battery and the final value of the actual capacity of the battery, taking the quotient of the difference and the time interval as the average descending speed of the actual capacity of the battery, and taking the average descending speed of the actual capacity of the battery as a threshold value of the descending speed of the actual capacity of the battery.
For example, the time length h of a single charge, the charge amount C of the single charge, the current I of the charge, the average temperature T of the battery and the actual capacity AC of the battery of the mobile phone for two years are collected and stored in the history database. The actual capacity value of the battery corresponding to the training sample with the earliest charging time is 100%, the actual capacity value of the battery corresponding to the training sample with the latest charging time is 70%, the time interval between the training sample with the earliest charging time and the training sample with the latest charging time is two years, namely the actual capacity of the battery is reduced from 100% to 70% in the two years, and then the average reduction speed of the actual capacity of the battery is as follows:
and setting the descending speed as a battery capacity descending speed threshold, namely a threshold of the charging control strategy.
S302, periodically judging whether the battery capacity reduction speed is less than or equal to a battery capacity reduction speed threshold value or not based on a parameter acquisition time interval; if yes, go to step 303, if no, go to step 304.
In one embodiment, the parameter collection time interval is 1 minute, the battery charging current parameter is periodically collected at an interval of 1 minute, and the battery charging current parameter is input into the battery actual capacity prediction model to obtain the battery actual capacity prediction value. The battery capacity decrease rate is also periodically calculated at 1 minute intervals, and it is determined whether the battery capacity decrease rate is less than or equal to the battery capacity decrease rate threshold.
S303, setting the charging input current to a preset maximum charging current.
And S304, setting the charging input current as a preset current corresponding to the minimum actual capacity reduction speed of the battery.
In one embodiment, a maximum charging current is set and a minimum battery actual capacity decrease rate is set based on charge experiment data performed for the battery, and a current corresponding to the minimum battery actual capacity decrease rate is set. Setting the charging input current to a maximum charging current if the battery capacity decrease rate is less than or equal to the battery capacity decrease rate threshold; if the battery capacity decrease rate is greater than the battery capacity decrease rate threshold, the charging input current is set to a current corresponding to the minimum battery actual capacity decrease rate.
In one embodiment, the actual battery capacity prediction model is a BP neural network model, a training sample is generated by using battery charging historical parameters stored in a historical database and corresponding actual battery capacity values, and the BP neural network model is trained offline; and calculating the average descending speed of the actual capacity of the battery according to the actual capacity change of the battery corresponding to the training sample, and taking the average descending speed as a threshold value of the descending speed of the actual capacity of the battery, namely the threshold value of the descending speed of the battery capacity.
When the charging request signal is in the power protection mode, the battery charging control method disclosed by the invention is used for charging; and when the charging request signal is in a quick charging mode, realizing quick charging according to the requirements of users. In the charging process of the battery, the actual capacity of the battery is predicted on line by using a BP neural network model, the actual capacity reduction speed of the battery is calculated, and when the actual capacity reduction speed of the battery is smaller than or equal to the battery capacity reduction speed threshold, the battery is charged by using the maximum charging current so as to obtain the fastest charging speed.
And when the actual capacity reduction speed of the battery is greater than the battery capacity reduction speed threshold, charging is carried out based on the current corresponding to the minimum actual capacity reduction speed of the battery, so that the actual capacity loss of the battery is reduced to the minimum, and the service life of the battery is prolonged. After charging is finished, the charging duration, the charging electric quantity, the charging current, the average temperature of the battery, the corresponding actual battery capacity value and other data are recorded and uploaded to the historical database.
As shown in fig. 4, the battery actual capacity prediction model is a BP neural network model. The BP neural network model comprises an input layer, a hidden layer and an output layer; the number of the neurons of the input layer is four, and the four neurons respectively correspond to the single charging time h, the single charging electric quantity C, the charging current I and the average temperature T of the battery. The number of the neurons of the output layer is one, and the neurons correspond to the battery actual capacity predicted value and the battery actual capacity training predicted value, namely the battery actual capacity AC. The number of neurons in the hidden layer is
Wherein h is the number of neurons in the hidden layer, m is the number of neurons in the input layer, n is the number of neurons in the output layer, and k is an adjustment constant of 1 to 10.
The constructed battery actual capacity prediction model can be trained by using various training methods. For example, the weight and the threshold of the BP neural network model are used as particles, and initialization is carried out; setting a fitness function according to the difference between the actual capacity training predicted value of the battery output by the output layer in the training process and the corresponding actual capacity true value of the battery; and in the training process, a particle swarm algorithm is adopted, and the weight and the threshold are optimized according to the fitness function, so that a trained battery actual capacity prediction model is obtained.
The excitation functions of the input layer and the output layer adopt a linear function purelin:
f (1) (x)＝f (3) (x)＝x (1-1)；
the excitation function of the hidden layer adopts an s-type function, and specifically comprises the following steps:
in order to avoid low learning efficiency, low convergence speed and local minimum value trapping of the BP neural network and increase the generalization performance of the network, the weight and the threshold of the BP neural network are optimized by adopting a Particle Swarm Optimization (PSO) algorithm. The particle optimization fitness function is:
wherein, the first and the second end of the pipe are connected with each other,
training a predicted value (battery actual capacity predicted value) for the battery actual capacity of an output node of the jth BP neural network model of the ith training sample, y j,i And n is the number of output neurons of the BP neural network model. As shown in fig. 4, the output neurons correspond to output nodes, are located in and constitute the output layer of the BP neural network model, and only have 1 output variable (output node), namely "battery capacity", in the present invention, and the function of the output neurons is to determine or predict the actual capacity of the battery.
Fig. 5 is a schematic flowchart of another embodiment of the battery charging control method of the present disclosure, where the method shown in fig. 5 includes the steps of: S501-S509. The following will explain each step.
S501, training the battery actual capacity prediction model by using the training samples offline.
In one embodiment, a BP neural network model is established and trained, and the BP neural network is optimized by using a particle swarm optimization in the training process to obtain a prediction model of the actual capacity of the battery.
S502, a charging request signal is received.
S503, judging whether the protection mode is adopted, if yes, the process goes to S504, and if not, the process goes to S505.
And S504, setting the charging input current as a preset maximum charging current.
And S505, obtaining a predicted value of the actual capacity of the battery on line by using a prediction model of the actual capacity of the battery, and calculating the reduction speed of the capacity of the battery.
S506, it is determined whether the battery capacity decrease speed is less than or equal to the battery capacity decrease speed threshold. If yes, the process proceeds to S507, and if no, the process proceeds to S508.
And S507, setting the charging input current as a preset maximum charging current.
S508, the charging input current is set to a current corresponding to the minimum battery actual capacity decrease rate.
S509, after the charging is completed, records and stores data corresponding to the charging.
The battery charging control method in the embodiment predicts the actual capacity of the battery, which is difficult to directly measure the variable, generates the optimal charging strategy of the battery according to whether the actual capacity reduction speed of the battery is greater than the set battery capacity reduction speed threshold, controls the charging module of the battery, controls the input current of charging, reduces the performance degradation of the battery caused by the charging irregularity, obtains the fastest charging speed under the condition of ensuring the optimal service life of the battery, and prolongs the service life of the battery.
In one embodiment, a BP neural network model is established and trained by using data stored in a historical database, and the BP neural network is optimized by using a particle swarm algorithm in the training process. The basic idea of Particle Swarm Optimization (PSO) is to find the optimal solution through collaboration and information sharing between individuals and groups, starting from a random solution. When the PSO is used for solving the optimization problem, an algorithm initializes a group of random particles, each particle has own speed and position, the particles update the speed and position through iteration each time, and each particle respectively updates the speed and position according to two simple rules: moving following the best solution found by the particles themselves, thereby obtaining individual optima; the best performing particle in the population is followed, thereby obtaining a global optimum. And calculating the fitness value of the particle according to the position of the particle so as to measure the quality of the particle, and by the method, all the particles reach a global optimal solution. The weights and thresholds of the BP neural network model can be optimized by using the existing particle swarm optimization algorithm.
Fig. 6 is a flowchart of the method for optimizing weight and threshold of the BP neural network model according to the present disclosure, and the method shown in fig. 6 includes the steps of: S601-S613. The following describes each step.
S601, preprocessing data.
S602, determining a network model structure. The network model is a BP neural network model.
And S603, initializing weights of the neural network.
S604, initializing a particle swarm. The weight and the threshold value in the BP neural network are compiled into particles, and the particles are initialized, wherein the initialization comprises the population scale, the initial position and the initial speed of the particles;
s605, calculate a fitness value. The fitness function may be a function of equations 1-3.
S606, updating Pbest and Gbest. Pbest is the optimal position that the particle itself has experienced, and Gbest is the optimal position that the particle swarm has experienced. In each iteration, the adaptive value of the new position obtained by each particle is compared with the optimal position experienced by the particle and the optimal position experienced by the whole particle swarm, and if the adaptive value is optimal, pbest or Gbest is updated.
S607, judging whether the maximum iteration number or the error requirement is reached, if yes, going to step S608, if no, going to step S605.
S608, determine the optimal network initialization weight threshold.
And S609, forward solving the output of the hidden layer and the output layer.
S610, calculating the deviation of the output layer.
And S611, reversely propagating the error. The training process is divided into two processes of information forward transmission and error backward transmission, and the weight and the threshold are corrected by transmitting an error signal.
S612, adjusting the weight and the threshold.
S613, judging whether the training sample is finished or not, and if so, finishing; if not, proceed to S609.
Exemplary devices
In one embodiment, as shown in fig. 7, the present disclosure provides a battery charge control device including: a training sample generation module 701, a predictive model training module 702, an actual capacity prediction module 703, a capacity variation determination module 704, and a charging current control module 705. The training sample generation module 701 obtains a battery charging history parameter and a corresponding actual battery capacity value, and generates a training sample based on the battery charging history parameter and the actual battery capacity value. The prediction model training module 702 trains the constructed battery actual capacity prediction model using the training samples.
When the actual capacity prediction module 703 charges the battery, it obtains the current parameter of battery charging, and uses the trained actual capacity prediction model of the battery and performs prediction processing according to the current parameter of battery charging to obtain the predicted value of the actual capacity of the battery. The capacity change determination module 704 determines a battery capacity change speed from the predicted value of the actual battery capacity. The charging current control module 705 controls the charging input current according to the rate of change of the battery capacity using a preset charging strategy.
In one embodiment, the capacity change determination module 704 obtains a battery actual capacity reference value, calculates a difference between the battery actual capacity prediction value and the battery actual capacity reference value, and calculates a battery capacity change speed based on the difference. And the battery actual capacity reference value comprises a battery actual capacity value after last charging or a battery actual capacity initial value corresponding to the training sample.
The battery charging historical parameters and the battery charging current parameters comprise single charging time length, single charging electric quantity, charging current, battery average temperature and the like; the actual capacity prediction module 703 sets a parameter collection time interval, periodically collects the current battery charging parameter based on the parameter collection time interval, and inputs the current battery charging parameter into the actual capacity prediction model to obtain the predicted value of the actual capacity of the battery output by the actual capacity prediction model.
In one embodiment, the battery capacity change rate includes a battery capacity decrease rate. As shown in fig. 8, charging current control module 705 includes a threshold value obtaining unit 7051 and a current setting unit 7052. Threshold acquisition unit 7051 determines a battery capacity decrease speed threshold; threshold obtaining unit 7051 obtains the initial value of the actual capacity of the battery and the final value of the actual capacity of the battery corresponding to the training samples; threshold obtaining unit 7051 calculates the average decrease speed of the actual capacity of the battery corresponding to the training sample from the initial value of the actual capacity of the battery and the final value of the actual capacity of the battery, and uses the average decrease speed of the actual capacity of the battery as a threshold of the decrease speed of the capacity of the battery.
Current setting unit 7052 periodically determines whether the battery capacity decrease speed is less than or equal to the battery capacity decrease speed threshold based on the parameter acquisition time interval; if so, the current setting unit 7052 sets the charging input current to a preset maximum charging current; if not, current setting unit 7052 sets the charging input current to a preset current corresponding to the minimum battery actual capacity decrease rate.
In one embodiment, as shown in fig. 9, the battery charging control apparatus further includes a charging data storage module 706 and a charging mode determination module 707. After the charging is completed, the charging data storage module 706 records and stores the single charging time, the single charging electric quantity, the charging current and the average temperature of the battery corresponding to the charging. The charging mode determination module 707 determines the charging mode based on the received charging request signal. If the charging mode is the protection mode, acquiring the current charging parameters of the battery, using a preset charging strategy and controlling the charging input current according to the capacity change speed of the battery; if the charging mode is the fast charging mode, current setting unit 7052 sets the charging input current to a preset maximum charging current.
In one embodiment, the battery actual capacity prediction model comprises a BP neural network model; the BP neural network model comprises an input layer, a hidden layer and an output layer; the prediction model training module 702 takes the weight and the threshold of the BP neural network model as particles, initializes the particles, and sets a fitness function according to the difference between the actual capacity training predicted value of the battery output by the output layer in the training process and the actual capacity true value of the corresponding battery; the prediction model training module 702 adopts a particle swarm algorithm in the training process and optimizes the weight and the threshold according to the fitness function to obtain a trained battery actual capacity prediction model.
Fig. 10 is a schematic structural diagram of a battery charge control device according to yet another embodiment of the present disclosure, and as shown in fig. 10, the battery charge control device 101 includes one or more processors 1011 and a memory 1012.
The processor 1011 may be a Central Processing Unit (CPU) or other form of processing unit having data processing capabilities and/or instruction execution capabilities, and may control other components in the battery charge control apparatus 101 to perform desired functions.
Memory 1012 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. Volatile memory, for example, may include: random Access Memory (RAM) and/or cache memory (cache), etc. The nonvolatile memory, for example, may include: read Only Memory (ROM), hard disk, flash memory, and the like. One or more computer program instructions may be stored on a computer readable storage medium and executed by the processor 1011 to implement the battery charge control methods of the various embodiments of the present disclosure above and/or other desired functions. Various contents such as an input signal, a signal component, a noise component, etc. may also be stored in the computer-readable storage medium.
In one example, the battery charge control apparatus 101 may further include: input device 1013, and output device 1014, etc., which are interconnected by a bus system and/or other form of connection mechanism (not shown). Further, the input device 1013 may include, for example, a keyboard, a mouse, and the like. The output device 1014 can output various kinds of information to the outside. The output devices 1014 may include, for example, a display, speakers, printer, and the like, as well as a communication network and remote output devices connected thereto.
Of course, for the sake of simplicity, only some of the components related to the present disclosure in this battery charge control apparatus 101 are shown in fig. 10, and components such as buses, input/output interfaces, and the like are omitted. In addition, the battery charge control device 101 may include any other suitable components depending on the particular application.
In one embodiment, the present disclosure provides a terminal including the battery charging control apparatus as in any of the above embodiments. The terminal can be a mobile phone, a notebook computer and the like.
In addition to the above-described methods and apparatus, embodiments of the present disclosure may also be a computer program product comprising computer program instructions that, when executed by a processor, cause the processor to perform the steps in the battery charge control method according to various embodiments of the present disclosure described in the "exemplary methods" section above of this specification.
The computer program product may write program code for carrying out operations for embodiments of the present disclosure in any combination of one or more programming languages, including an object oriented programming language such as Java, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device and partly on a remote computing device, or entirely on the remote computing device or server.
Furthermore, embodiments of the present disclosure may also be a computer-readable storage medium having stored thereon computer program instructions that, when executed by a processor, cause the processor to perform steps in a battery charge control method according to various embodiments of the present disclosure described in the "exemplary methods" section above in this specification.
The computer-readable storage medium may take any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may include, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium may include: an electrical connection having one or more wires, a portable disk, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
The basic principles of the present disclosure have been described above in connection with specific embodiments, but it should be noted that advantages, effects, and the like, mentioned in the present disclosure are only examples and not limitations, and should not be considered essential to the various embodiments of the present disclosure. Furthermore, the foregoing disclosure of specific details is for the purpose of illustration and description and is not intended to be limiting, since the disclosure will be described in detail with reference to specific details.
In the battery charging control method, the battery charging control device, the terminal and the storage medium in the above embodiments, the actual capacity of the battery is predicted in the charging process by constructing the actual capacity prediction model of the battery, and the optimal charging strategy of the battery is generated according to the determination result of determining whether the actual capacity reduction speed of the battery is greater than the battery capacity reduction speed threshold; the charging current can be automatically switched and adjusted in the charging process of the battery, the battery loss is reduced, and the effect of prolonging the service life of the battery is achieved; the charging module of the battery can be controlled, the input current of charging is controlled, the performance degradation of the battery caused by charging non-specification is reduced, the fastest charging speed is obtained under the condition that the service life of the battery is ensured to be optimal, and the customer experience is improved; by adopting the particle swarm optimization to optimize the BP neural network, the problems of low learning efficiency, low convergence rate and easy falling into local minimum value of the BP neural network are avoided,
in the present specification, the embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts in the embodiments are referred to each other. For the system embodiment, since it basically corresponds to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The block diagrams of devices, apparatuses, systems referred to in this disclosure are only given as illustrative examples and are not intended to require or imply that the connections, arrangements, configurations, etc. must be made in the manner shown in the block diagrams. These devices, apparatuses, devices, and systems may be connected, arranged, configured in any manner, as will be appreciated by those skilled in the art. Words such as "including," comprising, "having," and the like are open-ended words that mean "including, but not limited to," and are used interchangeably therewith. The words "or" and "as used herein mean, and are used interchangeably with, the word" and/or, "unless the context clearly dictates otherwise. The word "such as" is used herein to mean, and is used interchangeably with, the phrase "such as but not limited to".
The methods and apparatus of the present disclosure may be implemented in a number of ways. For example, the methods and apparatus of the present disclosure may be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above-described order for the steps of the method is for illustration only, and the steps of the method of the present disclosure are not limited to the order specifically described above unless specifically stated otherwise. Further, in some embodiments, the present disclosure may also be embodied as programs recorded in a recording medium, the programs including machine-readable instructions for implementing the methods according to the present disclosure. Thus, the present disclosure also covers a recording medium storing a program for executing the method according to the present disclosure.
It is also noted that in the devices, apparatuses, and methods of the present disclosure, each component or step can be decomposed and/or recombined. These decompositions and/or recombinations are to be considered equivalents of the present disclosure.
The previous description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects and the like will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other aspects without departing from the scope of the disclosure. Thus, the present disclosure is not intended to be limited to the aspects shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
The foregoing description has been presented for purposes of illustration and description. Furthermore, the description is not intended to limit embodiments of the disclosure to the form disclosed herein. While a number of example aspects and embodiments have been discussed above, those of skill in the art will recognize certain variations, modifications, alterations, additions and sub-combinations thereof.
Claims (8)
1. A battery charge control method, comprising:
acquiring a battery charging history parameter and a corresponding actual capacity value of a battery, and generating a training sample based on the battery charging history parameter and the actual capacity value of the battery;
training the constructed battery actual capacity prediction model by using the training sample;
when a battery is charged, acquiring current charging parameters of the battery, and performing prediction processing according to the current charging parameters of the battery by using a trained actual capacity prediction model of the battery to obtain a predicted value of the actual capacity of the battery;
determining the battery capacity change speed according to the predicted battery actual capacity value, wherein the method comprises the following steps:
acquiring a battery actual capacity reference value, calculating a difference value between the battery actual capacity predicted value and the battery actual capacity reference value, and calculating the battery capacity change speed based on the difference value; the battery actual capacity reference value includes: the actual capacity value of the battery after the last charging or the initial value of the actual capacity of the battery corresponding to the training sample;
controlling a charging input current according to the battery capacity change speed by using a preset charging strategy;
wherein the battery capacity change speed includes: the rate of decrease in battery capacity; acquiring an initial value of the actual capacity of the battery and a final value of the actual capacity of the battery corresponding to the training sample; calculating the average descending speed of the actual capacity of the battery corresponding to the training sample according to the initial value of the actual capacity of the battery and the final value of the actual capacity of the battery, and taking the average descending speed of the actual capacity of the battery as the threshold value of the descending speed of the actual capacity of the battery; periodically determining whether the battery capacity decrease rate is less than or equal to the battery capacity decrease rate threshold based on the parameter acquisition time interval; if yes, setting the charging input current as a preset maximum charging current; if not, setting the charging input current as a preset current corresponding to the minimum actual capacity reduction speed of the battery;
the battery actual capacity prediction model includes: a BP neural network model; the BP neural network model comprises an input layer, a hidden layer and an output layer; the training of the constructed battery actual capacity prediction model by using the training samples comprises:
taking the weight value and the threshold value of the BP neural network model as particles, and initializing;
setting a fitness function according to the difference between the actual capacity training predicted value of the battery output by the output layer in the training process and the corresponding actual capacity true value of the battery;
in the training process, a particle swarm algorithm is adopted, and the weight and the threshold are optimized according to the fitness function, so that a trained battery actual capacity prediction model is obtained;
the excitation functions of the input layer and the output layer adopt linear functions; the excitation function of the hidden layer adopts an s-type function;
the fitness function is:
wherein, the first and the second end of the pipe are connected with each other,
training a predicted value, y, for the battery actual capacity of the output node of the jth BP neural network model of the ith training sample j,i The actual capacity true value of the battery corresponding to the jth output node of the ith training sample is obtained, and n is the number of output neurons of the BP neural network model;
the battery charging history parameter and the battery charging current parameter include: single charge duration, single charge capacity, charge current, average battery temperature; the number of the neurons of the input layer is four, and the four neurons respectively correspond to the single charging time, the single charging electric quantity, the charging current and the average temperature of the battery; the number of the neurons of the output layer is one, and the neurons correspond to the battery actual capacity predicted value and the battery actual capacity training predicted value; the number of neurons of the hidden layer is
Wherein h is the neuron number of the hidden layer, m is the neuron number of the input layer, n is the neuron number of the output layer, and k is an adjustment constant of 1 to 10.
2. The method of claim 1, wherein the performing a prediction process according to the battery charging current parameter using the trained battery actual capacity prediction model to obtain a battery actual capacity prediction value comprises:
setting a parameter acquisition time interval;
periodically acquiring the current battery charging parameters based on the parameter acquisition time interval, inputting the current battery charging parameters into the actual battery capacity prediction model, and acquiring the predicted value of the actual battery capacity output by the actual battery capacity prediction model.
3. The method of claim 2, further comprising:
after the charging is finished, recording and storing the single charging time, the single charging electric quantity, the charging current and the average temperature of the battery corresponding to the charging.
4. The method of any of claims 1 to 3, further comprising:
determining a charging mode based on the received charging request signal;
if the charging mode is the protection mode, acquiring the current charging parameters of the battery, using a preset charging strategy and controlling the charging input current according to the change speed of the battery capacity;
and if the charging mode is the quick charging mode, setting the charging input current as a preset maximum charging current.
5. A battery charge control device comprising:
the training sample generating module is used for acquiring a battery charging history parameter and a corresponding actual battery capacity value and generating a training sample based on the battery charging history parameter and the actual battery capacity value;
the prediction model training module is used for training the constructed battery actual capacity prediction model by using the training samples;
the actual capacity prediction module is used for acquiring the current battery charging parameter when the battery is charged, and performing prediction processing according to the current battery charging parameter by using a trained actual capacity prediction model to acquire the predicted value of the actual capacity of the battery;
the capacity change determining module is used for determining the battery capacity change speed according to the predicted value of the actual capacity of the battery;
the capacity change determining module is specifically configured to obtain a battery actual capacity reference value, calculate a difference between a battery actual capacity predicted value and the battery actual capacity reference value, and calculate a battery capacity change speed based on the difference, where the battery actual capacity reference value includes a battery actual capacity value after last charging or a battery actual capacity initial value corresponding to a training sample;
the charging current control module is used for controlling charging input current according to the change speed of the battery capacity by using a preset charging strategy;
wherein the battery capacity change speed includes: the rate of decrease in battery capacity; the charging current control module comprises a threshold value acquisition unit and a current setting unit, wherein the threshold value acquisition unit is used for acquiring an initial value of the actual capacity of the battery and a final value of the actual capacity of the battery corresponding to the training sample; calculating the average descending speed of the actual capacity of the battery corresponding to the training sample according to the initial value of the actual capacity of the battery and the final value of the actual capacity of the battery, and taking the average descending speed of the actual capacity of the battery as a threshold value of the descending speed of the capacity of the battery; the current setting unit is used for periodically judging whether the battery capacity reduction speed is less than or equal to a battery capacity reduction speed threshold value or not based on the parameter acquisition time interval; if yes, setting the charging input current as a preset maximum charging current; if not, setting the charging input current as a preset current corresponding to the minimum actual capacity reduction speed of the battery;
the actual battery capacity prediction model comprises a BP neural network model; the BP neural network model comprises an input layer, a hidden layer and an output layer; the prediction model training module is specifically used for taking the weight and the threshold of the BP neural network model as particles and initializing the particles; setting a fitness function according to the difference between the actual capacity training predicted value of the battery output by the output layer in the training process and the corresponding actual capacity true value of the battery; in the training process, a particle swarm algorithm is adopted, and the weight and the threshold are optimized according to the fitness function, so that a trained battery actual capacity prediction model is obtained;
the excitation functions of the input layer and the output layer adopt linear functions; the excitation function of the hidden layer adopts an s-type function; the fitness function is:
wherein the content of the first and second substances,
training a predicted value, y, for the battery actual capacity of the output node of the jth BP neural network model of the ith training sample j,i The actual capacity real value of the battery corresponding to the jth output node of the ith training sample is obtained, and n is the number of output neurons of the BP neural network model;
the battery charging history parameter and the battery charging current parameter include: single charging time, single charging electric quantity, charging current and average temperature of the battery; the number of the neurons of the input layer is four, and the four neurons respectively correspond to the single charging time, the single charging electric quantity, the charging current and the average temperature of the battery; the number of the neurons of the output layer is one, and the neurons correspond to the battery actual capacity predicted value and the battery actual capacity training predicted value; the number of neurons of the hidden layer is
Wherein h is the neuron number of the hidden layer, m is the neuron number of the input layer, n is the neuron number of the output layer, and k is an adjustment constant of 1 to 10.
6. A battery charge control device comprising:
a processor; a memory for storing the processor-executable instructions;
the processor is used for reading the executable instruction from the memory and executing the instruction to realize the method of any one of the above claims 1-4.
7. A terminal, comprising:
the battery charge control apparatus according to any one of claims 5 to 6.
8. A computer-readable storage medium, the storage medium storing a computer program for performing the method of any of the preceding claims 1-4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010935594.0A CN112018854B (en) | 2020-09-08 | 2020-09-08 | Battery charging control method, device, terminal and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010935594.0A CN112018854B (en) | 2020-09-08 | 2020-09-08 | Battery charging control method, device, terminal and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112018854A CN112018854A (en) | 2020-12-01 |
| CN112018854B true CN112018854B (en) | 2022-11-15 |
Family
ID=73516567
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010935594.0A Active CN112018854B (en) | 2020-09-08 | 2020-09-08 | Battery charging control method, device, terminal and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112018854B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113258154B (en) * | 2021-07-16 | 2021-10-15 | 苏州浪潮智能科技有限公司 | Battery charging method, device, equipment and medium |
| CN113687250B (en) * | 2021-08-18 | 2023-10-24 | 蜂巢能源科技有限公司 | Battery cell capacity prediction method and device, electronic equipment and medium |
| CN113978311B (en) * | 2021-10-15 | 2024-05-17 | 潍柴动力股份有限公司 | Battery temperature correction method and device and electronic equipment |
| CN114347834B (en) * | 2021-12-03 | 2024-05-10 | 北京车和家汽车科技有限公司 | Vehicle control method, and method and device for generating charge duration prediction model |
| CN114487848B (en) * | 2022-01-17 | 2024-05-03 | 北京和利时系统集成有限公司 | State calculation method and device for storage battery |
| CN116231803B (en) * | 2023-03-02 | 2024-01-23 | 深圳市华南英才科技有限公司 | Quick charging method and device for capacitive pen and storage medium |
| CN116160878B (en) * | 2023-04-25 | 2023-07-18 | 浙江新诺力电源科技有限公司 | Battery replacement control system and method, computer readable medium and electronic equipment |
| CN117277519B (en) * | 2023-11-21 | 2024-02-02 | 深圳鹏城新能科技有限公司 | Method, system and medium for protecting energy storage inverter battery from overcharge |
| CN117755150A (en) * | 2023-11-28 | 2024-03-26 | 北京潞电电力建设有限公司 | Quick charging method based on machine learning |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9263912B2 (en) * | 2013-02-05 | 2016-02-16 | Dell Products, L.P. | Mitigating premature wear out of a rechargeable battery |
| US9800073B2 (en) * | 2015-08-20 | 2017-10-24 | International Business Machines Corporation | Modeling a change in battery degradation |
| KR102483644B1 (en) * | 2017-04-28 | 2023-01-02 | 삼성전자주식회사 | Method and apparatus of predicting capacity fade rate of a rechargeable battery |
| US10931128B2 (en) * | 2017-04-28 | 2021-02-23 | Samsung Electronics Co., Ltd. | Method and apparatus to predict capacity fade rate of battery |
| CN107831441B (en) * | 2017-09-20 | 2019-11-05 | 哈尔滨理工大学 | Prediction technique, forecasting system and a kind of charging unit of lithium battery charging current |
| CN110794308B (en) * | 2019-11-07 | 2021-09-10 | 交控科技股份有限公司 | Method and device for predicting train battery capacity |
-
2020
- 2020-09-08 CN CN202010935594.0A patent/CN112018854B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112018854A (en) | 2020-12-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112018854B (en) | Battery charging control method, device, terminal and storage medium | |
| KR20200100626A (en) | System and method for optimal control of energy storage system | |
| US20200191117A1 (en) | Adaptive dynamic planning control method and system for energy storage station, and storage medium | |
| JP2019528032A (en) | Battery management system | |
| US20180166880A1 (en) | Data-Driven Demand Charge Management Solution | |
| CN111046018A (en) | Multi-objective optimization-based power generation equipment operation condition library construction method and device | |
| CN110414748B (en) | Photovoltaic power prediction method | |
| CN115236526A (en) | Method and device for predicting residual charging time, storage medium and vehicle | |
| CN111781507A (en) | SOC value display method and device and energy storage system | |
| CN115759317A (en) | Power load regulation and control method and device, electronic equipment and storage medium | |
| KR102297543B1 (en) | Apparatus and method for predicting state of charge of battery | |
| EP4293373A1 (en) | Method and apparatus with battery short detection | |
| CN116937560A (en) | New energy output prediction method, device, equipment and readable storage medium | |
| CN116861256A (en) | Furnace temperature prediction method, system, equipment and medium for solid waste incineration process | |
| CN112329995A (en) | Optimal scheduling method and device for distributed energy storage cluster and computer equipment | |
| CN115001002A (en) | Optimal scheduling method and system for solving energy storage participation peak clipping and valley filling | |
| CN113919217A (en) | Self-adaptive parameter setting method and device for active disturbance rejection controller | |
| Wokoma et al. | Predicting Voltage Stability Indices of Nigerian 330kV 30 Bus Power Network Using an Auditory Machine Intelligence Technique | |
| CN118095783B (en) | Electric automobile charging planning method and device | |
| Seshagiri et al. | An Empirical Study of On-Policy and Off-Policy Actor-Critic Algorithms in the Context of Exploration-Exploitation Dilemma | |
| US20240119281A1 (en) | Ai based techniques for photovoltaic interruption control in microgrids with energy storage systems | |
| CN117061605B (en) | Intelligent lithium battery active information pushing method and device based on end cloud cooperation | |
| CN115914227B (en) | Edge internet of things proxy resource allocation method based on deep reinforcement learning | |
| WO2024057581A1 (en) | Charge-state calculation device | |
| Bhatt et al. | A fast and efficient back propagation algorithm to forecast active and reactive power drawn by various capacity Induction Motors |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |