CN115184805A

CN115184805A - Battery health state acquisition method, device, equipment and computer program product

Info

Publication number: CN115184805A
Application number: CN202210708124.XA
Authority: CN
Inventors: 陈英杰; 侯岩凯; 蔡国全
Original assignee: Dongguan Poweramp Technology Ltd
Current assignee: Dongguan Poweramp Technology Ltd
Priority date: 2022-06-21
Filing date: 2022-06-21
Publication date: 2022-10-14

Abstract

The application discloses a battery health state acquisition method, a battery health state acquisition device, a battery health state acquisition equipment and a computer program product. The method comprises the following steps: receiving operation condition data of the first electric equipment, wherein the operation condition data of the first electric equipment comprises at least one of charging condition data, discharging condition data and standing condition data of the first electric equipment; determining a first characteristic parameter according to the operation condition data of the first electric equipment; inputting the first characteristic parameter into a target model matched with the first characteristic parameter to obtain a first maximum available capacity of the first battery; wherein the first maximum available capacity is used to indicate a current state of health of a first battery, the first battery being a battery of the first electrically powered device. According to the method and the device, the charging working condition data, the discharging working condition data or the standing working condition data of the electric equipment can be utilized, and the current health state of the battery of the electric equipment can be accurately predicted by means of the target model, so that the use reliability of the electric equipment can be improved.

Description

Battery health state acquisition method, device, equipment and computer program product

Technical Field

The present application relates to the field of battery technologies, and in particular, to a method, an apparatus, a device, and a computer program product for acquiring a battery health status.

Background

Along with the popularization of the environment-friendly concept of energy conservation and emission reduction, more and more electric equipment is put into use. Lithium ion batteries are widely used as energy storage devices in electric devices due to their advantages in energy density, cycle life, and the like. However, during the use of the battery, the performance of the battery inevitably decreases with the passage of time, and in order to ensure the operational reliability and accurately predict the State of Health (SOH), a technical problem to be solved is now urgently needed.

Disclosure of Invention

The embodiment of the application provides a method, a device, equipment and a computer program product for acquiring the battery health state, which can solve the problem of acquiring the battery health state.

In a first aspect, an embodiment of the present application provides a method for acquiring a state of health of a battery, including: receiving operation condition data of first electric equipment, wherein the operation condition data of the first electric equipment comprises at least one of charging condition data, discharging condition data and standing condition data of the first electric equipment; determining a first characteristic parameter according to the operation condition data of the first electric equipment; inputting the first characteristic parameter into a target model matched with the first characteristic parameter to obtain a first maximum available capacity of a first battery; wherein the first maximum available capacity is used to indicate a current state of health of the first battery, the first battery being a battery of the first electrically powered device.

In some embodiments, the operating condition data of the first electrically powered device comprises charging condition data of the first electrically powered device; the first characteristic parameter comprises at least one of: at least one charge voltage sample of the first battery; a slope of an open circuit voltage curve of the first cell; a maximum value of a differential capacity curve of the first cell and a voltage corresponding to the maximum value; the starting time of the first time period is the time when the first battery is changed from constant-current charging to constant-voltage charging, and the ending time of the first time period is the time when the first battery is fully charged; the target model is a first model obtained by training based on aging cycle test data of a second battery, charging condition data of second electric equipment and the calibrated maximum available capacity of the second battery, wherein the batteries of the first battery, the second battery and the second electric equipment are all target-type batteries.

In some embodiments, before the inputting the first characteristic parameter into the target model matched with the first characteristic parameter to obtain the first maximum available capacity of the first battery, the method further comprises: acquiring aging cycle test data of the second battery; acquiring charging condition data of the second electric equipment; counting the charging working condition data of the second electric equipment to obtain a statistical result, wherein the statistical result comprises an actual charging interval and a data sampling frequency of the target type battery; segmenting the aging cycle test data according to the actual charging interval to obtain first test data; resampling the first test data according to the data sampling frequency to obtain second test data; determining a second characteristic parameter according to the second test data, wherein the second characteristic parameter comprises at least one of the following items: at least one charge voltage sample of the second battery; a slope of an open circuit voltage curve of the second cell; a maximum value of a differential capacity curve of the second battery and a voltage corresponding to the maximum value; the starting time of the second time period is the time when the second battery is changed from constant current charging to constant voltage charging, and the ending time of the second time period is the time when the second battery is fully charged; and training the first model according to the second characteristic parameter and the calibrated maximum available capacity of the second battery.

In some embodiments, the operation condition data of the first electric device is discharge condition data or standing condition data of the first electric device; the first characteristic parameter comprises at least one of: an accumulated mileage of the first electrically powered device; an accumulated charge amount of the first battery; an accumulated discharge capacity of the first battery; the sum of the accumulated charge amount and the accumulated discharge amount of the first battery; a temperature of the first battery; the target model is a second model, and the second model is obtained based on charging condition data of third electric equipment and training of the first model; the first model is obtained based on aging cycle test data of a second battery, charging condition data of second electric equipment and calibrated maximum available capacity training of the second battery; the first battery, the second battery, the battery of the second electric device and the battery of the third electric device are all target-type batteries.

In some embodiments, before the inputting the first characteristic parameter into the target model matched with the first characteristic parameter to obtain the first maximum available capacity of the first battery, the method further comprises: acquiring operation condition data of the third electric equipment, wherein the operation condition data of the third electric equipment at least comprises charging condition data of the third electric equipment; determining a third characteristic parameter and a fourth characteristic parameter according to the operating condition data of the third electric equipment; inputting the third characteristic information into the first model to obtain a second maximum available capacity of a third battery, wherein the third battery is a battery of the third electric equipment; training the second model according to the fourth characteristic parameter and the second maximum available capacity; wherein the third characteristic parameter comprises at least one of: at least one charge voltage sample of the third battery; a slope of an open circuit voltage curve of the third cell; a maximum value of a differential capacity curve of the third battery and a voltage corresponding to the maximum value; the starting time of the third time period is the time when the third battery is changed from constant current charging to constant voltage charging, and the ending time of the third time period is the time when the third battery is fully charged; the fourth characteristic parameter comprises at least one of: the accumulated mileage of the third electric equipment, the accumulated charge amount of the third battery, the accumulated discharge amount of the third battery, the sum of the accumulated charge amount and the accumulated discharge amount of the third battery, and the temperature of the third battery.

In a second aspect, an embodiment of the present application provides a battery state of health obtaining apparatus, including: the first receiving module is used for receiving operation condition data of first electric equipment, wherein the operation condition data of the first electric equipment comprises at least one of charging condition data, discharging condition data and standing condition data of the first electric equipment; the first determining module is used for determining a first characteristic parameter according to the operating condition data of the first electric equipment; the first operation module is used for inputting the first characteristic parameter into a target model matched with the first characteristic parameter to obtain a first maximum available capacity of the first battery; wherein the first maximum available capacity is used to indicate a current state of health of the first battery, the first battery being a battery of the first electrically powered device.

In some embodiments, the apparatus further comprises: the first acquisition module is used for acquiring aging cycle test data of the second battery; the second acquisition module is used for acquiring charging working condition data of the second electric equipment; the statistical module is used for performing statistics on charging working condition data of the second electric equipment to obtain a statistical result, and the statistical result comprises an actual charging interval and data sampling frequency of the target type battery; the segmentation module is used for segmenting the aging cycle test data according to the actual charging interval to obtain first test data; the sampling module is used for resampling the first test data according to the data sampling frequency to obtain second test data; a second determining module, configured to determine a second characteristic parameter according to the second test data, where the second characteristic parameter includes at least one of: at least one charge voltage sample of the second battery; a slope of an open circuit voltage curve of the second cell; a maximum value of a differential capacity curve of the second battery and a voltage corresponding to the maximum value; the starting time of the second time period is the time when the second battery is changed from constant current charging to constant voltage charging, and the ending time of the second time period is the time when the second battery is fully charged; and the first training module is used for training the first model according to the second characteristic parameter and the calibrated maximum available capacity of the second battery.

In some embodiments, the operating condition data of the first electric device is discharge condition data or standing condition data of the first electric device; the first characteristic parameter comprises at least one of: the accumulated mileage of the first electric equipment, the accumulated charge amount of the first battery, the accumulated discharge amount of the first battery, the sum of the accumulated charge amount and the accumulated discharge amount of the first battery, and the temperature of the first battery; the target model is a second model, and the second model is obtained based on charging condition data of third electric equipment and training of the first model; the first model is obtained based on aging cycle test data of a second battery, charging condition data of second electric equipment and calibrated maximum available capacity training of the second battery; the first battery, the second battery, the battery of the second electric device and the battery of the third electric device are all target-type batteries.

In some embodiments, the apparatus further comprises: the third acquisition module is used for acquiring the operating condition data of the third electric equipment, wherein the operating condition data of the third electric equipment at least comprises the charging condition data of the third electric equipment; the third determining module is used for determining a third characteristic parameter and a fourth characteristic parameter according to the operation condition data of the third electric equipment; a second operation module, configured to input the third feature information into the first model to obtain a second maximum available capacity of a third battery, where the third battery is a battery of the third electric device; a second training module, configured to train the second model according to the fourth feature parameter and the second maximum available capacity; wherein the third characteristic parameter comprises at least one of: at least one charge voltage sample of the third battery; a slope of an open circuit voltage curve of the third cell; a maximum value of a differential capacity curve of the third cell and a voltage corresponding to the maximum value; the starting time of the third time period is the time when the third battery is changed from constant current charging to constant voltage charging, and the ending time of the third time period is the time when the third battery is fully charged; the fourth characteristic parameter comprises at least one of: an accumulated mileage of the third electrically powered device, an accumulated charge of the third battery, an accumulated discharge of the third battery, a sum of an accumulated charge and an accumulated discharge of the third battery, and a temperature of the third battery.

In a third aspect, an embodiment of the present application provides an electronic device, where the device includes: a processor and a memory storing computer program instructions; the processor, when executing the computer program instructions, implements a battery state of health acquisition method as described in any of the above.

In a fourth aspect, an embodiment of the present application provides a computer storage medium, where computer program instructions are stored, and when executed by a processor, the computer program instructions implement the battery health status obtaining method as described in any one of the above.

In a fifth aspect, the present application provides a computer program product, where when executed by a processor of an electronic device, an instruction of the computer program product causes the electronic device to execute the battery health status acquiring method as described in any one of the above.

In the embodiment of the application, a first characteristic parameter may be determined based on received operation condition data of a first electric device, where the operation condition data of the first electric device includes at least one of charging condition data, discharging condition data, and standing condition data of the first electric device; and then, inputting the first characteristic parameters into the matched target model, and predicting the maximum available capacity of the battery of the first electric device through the target model, wherein the maximum available capacity is used for indicating the current state of health of the battery of the first electric device. Therefore, the charging working condition data, the discharging working condition data or the standing working condition data of the electric equipment can be utilized, the current health state of the battery of the electric equipment can be accurately predicted by means of the target model, and therefore the use reliability of the electric equipment can be improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required to be used in the embodiments of the present application will be briefly described below.

Fig. 1 is a schematic flow chart of a battery state of health obtaining method according to an embodiment of the present disclosure;

FIG. 2 is a diagram of an idea of battery state of health acquisition provided by an embodiment of the present application;

fig. 3 is a second schematic flowchart of a battery health status obtaining method according to an embodiment of the present disclosure;

fig. 4 is a schematic structural diagram of a battery state of health obtaining apparatus according to an embodiment of the present application;

fig. 5 is a schematic structural diagram of a battery state of health obtaining device according to an embodiment of the present application.

Detailed Description

Features and exemplary embodiments of various aspects of the present application will be described in detail below, and in order to make objects, technical solutions and advantages of the present application more apparent, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are intended to be illustrative only and are not intended to be limiting. The following description of the embodiments is merely intended to provide a better understanding of the present application by illustrating examples thereof.

It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising 8230; \8230;" comprises 8230; "does not exclude the presence of additional like elements in a process, method, article, or apparatus that comprises the element.

The method for acquiring the state of health of a battery provided by the embodiments of the present application is described in detail below with reference to the accompanying drawings by using some embodiments and application scenarios thereof.

The battery health status acquiring method according to the embodiment of the present application may be executed by a battery health status acquiring device, and in a specific implementation manner, the battery health status acquiring device may be a cloud platform or a server.

Referring to fig. 1, fig. 1 is a flowchart of a battery state of health obtaining method provided in an embodiment of the present application. As shown in fig. 1, the battery state of health acquiring method may include the steps of:

101, receiving operation condition data of first electric equipment, wherein the operation condition data of the first electric equipment comprises at least one of charging condition data, discharging condition data and standing condition data of the first electric equipment.

The first electrically powered device may be any electrically powered device that is actually operating. The electric equipment can be an electric automobile, an electric two-wheeled vehicle, an electric motorcycle, an unmanned aerial vehicle or the like.

In an alternative embodiment, the first electrically powered device may periodically send its current operating condition data to the battery state of health obtaining device. In this embodiment, the first electric device may transmit its current operation condition data to the battery state of health obtaining device when the cycle transmission time of the operation condition data is reached.

In another alternative embodiment, the first electrically powered device may send its current operating condition data to the battery state of health obtaining device in response to a user indication. In this embodiment, if the user of the first electric device wants to know the current state of health of the battery of the first electric device, an indication message for indicating to obtain the current state of health of the battery of the first electric device may be input into the first electric device. The first electrically powered device may send its current operating condition data to the battery state of health acquisition device in response to the indication.

In the embodiment of the present application, the operation condition data of the first electric device may have the following expression form:

expression form 1: the operation condition data of the first electric device only comprises charging condition data of the first electric device;

expression form 2: the operation condition data of the first electric device may only include discharge condition data or standing condition data of the first electric device;

expression form 3: the operation condition data of the first electric device may include charging condition data, discharging condition data, and standing condition data of the first electric device.

It is understood that the reason why the operation condition data of the first electric device is expressed in the expression 2 may include at least any one of the following:

first electric equipment does not have operating mode data upload of charging, if: when charging a battery of the first electrically powered device (hereinafter referred to as a first battery), the first electrically powered device needs to be taken out of the first electrically powered device and charged in a dedicated charging device;

the first electric equipment forbids uploading of charging working condition data, if: in consideration of privacy protection, a user prohibits the first electric equipment from uploading charging working condition data;

the first electric equipment is powered off, so that charging working condition data are not uploaded;

and the first electric equipment is used for missing charging working condition data.

In practical applications, the charging condition data of the first electrically powered device may include, but is not limited to, at least one of the following: a charging current of the first battery; a charging voltage of the first battery; a State Of Charge (SOC) interval Of the first battery, which may also be referred to as a charging interval; an accumulated mileage of the first electrically powered device; the temperature of the first battery, etc.

The discharge condition data or rest condition data of the first electrically powered device may include, but is not limited to, at least one of: an accumulated mileage of the first electrically powered device; the temperature of the first battery, etc.

As can be seen from the above, the same type of data may exist in the charging condition data, the discharging condition data, and the standing condition data, such as: accumulated mileage, battery temperature, etc.

And 102, determining a first characteristic parameter according to the operating condition data of the first electric equipment.

In one specific implementation manner, the first characteristic parameter may be obtained by extracting or processing operation condition data of the first electric device. It is understood that, for the operating condition data of the first electric device in different expressions, the expressions of the first characteristic parameter may be the same or different, and are expressed as:

with respect to the operation condition data of the first electrically-operated device of expression 1 above, the first characteristic parameter is determined based on the charge condition data of the first electrically-operated device.

For the operation condition data of the first electric equipment of expression 2 above, the first characteristic parameter is determined based on the discharge condition data or the rest condition data of the first electric equipment.

For the operation condition data of the first electric device of expression 3 above, the first characteristic parameter may be determined based on at least one of charging condition data, discharging condition data, and standing condition data of the first electric device. It is to be understood that, in the case where the first characteristic parameter is determined based on the charging condition data, the discharging condition data, and the stationary condition data of the first electrically powered device, the first characteristic parameter may include a first sub-characteristic parameter determined based on the charging condition data of the first electrically powered device, and a second sub-characteristic parameter determined based on the discharging condition data or the stationary condition data of the first electrically powered device.

In the embodiment of the present application, the characteristic parameter determined based on the charging condition data of the first electrically powered device may include, but is not limited to, at least one of the following:

at least one charge voltage sample value of the first battery (which may also be referred to as a voltage sequence of the first battery); a slope of an Open Circuit Voltage (OCV) curve of the first battery; a maximum value of the differential capacity curve of the first cell and a voltage corresponding to the maximum value (which may also be referred to as a peak position of the differential capacity curve of the first cell); the starting time of the first time period is the time when the first battery changes from constant-current charging to constant-voltage charging (which may also be referred to as a constant-current constant-voltage (CCCV) change point), and the ending time of the first time period is the time when the first battery is fully charged, and the like.

In one particular implementation, the OCV curve may be an SOC-OCV curve.

The characteristic parameter determined based on the discharge condition data or the rest condition data of the first electrically powered device may include, but is not limited to, at least one of:

an accumulated mileage of the first electrically powered device; an accumulated charge amount of the first battery; an accumulated discharge capacity of the first battery; the sum of the accumulated charge amount and the accumulated discharge amount of the first battery; the temperature of the first battery, etc. The accumulated charge amount, the accumulated discharge amount, and the sum of the accumulated charge amount and the accumulated discharge amount may be collectively referred to as a capacity throughput.

It can be understood that the discharge condition data and the standing condition data both belong to the case of no charge condition data, and therefore, the manner of determining the characteristic parameter based on the discharge condition data or the standing condition data of the first electric device is the same.

And 103, inputting the first characteristic parameter into a target model matched with the first characteristic parameter to obtain a first maximum available capacity of the first battery.

Wherein the first maximum available capacity is used to indicate a current state of health of the first battery, the first battery being a battery of the first electrically powered device.

In this embodiment, the battery state of health obtaining device may have two models trained in advance, which are a first model and a second model. The outputs of the first and second models are both the maximum available capacity of the battery, but the inputs differ.

The input of the first model is a characteristic parameter determined based on charging condition data of the electric equipment; and the input of the second model is a characteristic parameter determined based on the discharge working condition data or the standing working condition data of the electric equipment. Based on the model inputs, it is understood that the first model may be used to predict a maximum available capacity of a battery of the electric device that uploaded the charging condition data; the second model may be used to predict a maximum available capacity of a battery of the electrical device that does not upload charging condition data, i.e., upload discharging condition data or standing condition data.

Therefore, in the case where the first characteristic parameter is determined based on the charging condition data of the first electrically powered device, the target model may be the first model described above. In this case, the output of the first model is the maximum available capacity of the first battery, i.e., the first maximum available capacity.

In a case where the first characteristic parameter is determined based on discharge condition data or rest condition data of the first electric device, the target model may be the above-described second model. In this case, the output of the second model is the first maximum available capacity.

In a case where the first feature parameter includes the above-described first sub-feature parameter and second sub-feature parameter, the object model may include the first model and the second model. During specific implementation, the first sub-characteristic parameter is input into the first model to obtain a first maximum available capacity; and inputting the second sub-characteristic parameter into the second model to obtain a second maximum available capacity. In one implementation, an average of the two maximum available capacities may be determined as a first maximum available capacity; in another implementation, a weighted sum of the two maximum available capacities may be determined as the first maximum available capacity, and a weighted value of the maximum available capacities predicted based on different models may be preset based on actual demands, such as: a weight value of the maximum available capacity predicted based on the first model may be set to 0.8; the weight value of the maximum available capacity predicted based on the first model is set to 0.2.

In the battery health status obtaining method of this embodiment, a first characteristic parameter may be determined based on received operating condition data of a first electric device, where the operating condition data of the first electric device includes at least one of charging condition data, discharging condition data, and standing condition data of the first electric device; and then, inputting the first characteristic parameters into the matched target model, and predicting the maximum available capacity of the battery of the first electric device through the target model, wherein the maximum available capacity is used for indicating the current state of health of the battery of the first electric device. Therefore, the charging working condition data, the discharging working condition data or the standing working condition data of the electric equipment can be utilized, the current health state of the battery of the electric equipment can be accurately predicted by means of the target model, and therefore the use reliability of the electric equipment can be improved.

In some embodiments, the operating condition data of the first electrically powered device comprises charging condition data of the first electrically powered device;

the first characteristic parameter comprises at least one of: at least one charge voltage sample of the first battery; a slope of an open circuit voltage curve (e.g., SOC-OCV curve) of the first battery; a maximum value of a differential capacity curve of the first battery and a voltage corresponding to the maximum value; the starting time of the first time period is the time when the first battery is changed from constant-current charging to constant-voltage charging, and the ending time of the first time period is the time when the first battery is fully charged;

the target model is a first model, and the first model is obtained based on aging cycle test data of a second battery, charging condition data of second electric equipment and calibrated maximum available capacity training of the second battery, wherein the batteries of the first battery, the second battery and the second electric equipment are all target-type batteries.

In this embodiment, the first characteristic parameter is determined based on the charging condition data of the first electric device, and the first characteristic parameter may be regarded as a health factor of the first battery.

The second cell is a cell for aging cycle testing; the second electrically powered device is an electrically powered device used to train the first model, and the second electrically powered device is an electrically powered device that is actually running.

Further, the battery of the second electrically powered device, the battery of the first electrically powered device, and the second battery may be the same model of battery, i.e., a target model of battery. Therefore, the maximum available capacity of the first battery is predicted by using the first model obtained by training based on the aging cycle test data of the second battery, the charging condition data of the second electric equipment and the calibrated maximum available capacity of the second battery, and the reliability of acquiring the battery health state of the first battery can be improved.

The same size of the battery can be represented by the same performance parameter of at least one of the following batteries: capacity; cell material; chemical constitution; chemical materials, and the like. Such as: the first battery, the second battery and the second electric equipment are all lithium iron phosphate batteries, ternary batteries, lithium cobalt oxide batteries, sodium ion batteries or solid-state batteries and the like. In one specific implementation manner, the first battery, the second battery, and the battery of the second electric device may be embodied as: cells of the same electrochemical system, or cells of the same batch on the same production line, or cells of different batches but with similar or identical performance parameters.

The training of the first model is specifically described below.

In some embodiments, before the inputting the first characteristic parameter into the target model matched with the first characteristic parameter to obtain the first maximum available capacity of the first battery, the method further comprises:

acquiring aging cycle test data of the second battery;

acquiring charging condition data of the second electric equipment;

counting the charging working condition data of the second electric equipment to obtain a statistical result, wherein the statistical result comprises an actual charging interval and a data sampling frequency of the target type battery;

segmenting the aging cycle test data according to the actual charging interval to obtain first test data;

resampling the first test data according to the data sampling frequency to obtain second test data;

determining a second characteristic parameter according to the second test data, wherein the second characteristic parameter comprises at least one of the following items: at least one charge voltage sample of the second battery; a slope of an open circuit voltage curve (e.g., SOC-OCV curve) of the second battery; a maximum value of a differential capacity curve of the second battery and a voltage corresponding to the maximum value; the starting time of the second time period is the time when the second battery is changed from constant current charging to constant voltage charging, and the ending time of the second time period is the time when the second battery is fully charged;

and training the first model according to the second characteristic parameter and the calibrated maximum available capacity of the second battery.

The aging cycle test data is data collected by an aging cycle test conducted in a laboratory. In the aging cycle test, the charging conditions are accurate and consistent, the battery is fully charged, namely the SOC interval is 0-100%, and the sampling frequency of data is large, for example, data is acquired once in 100 milliseconds (ms).

However, for an electrically operated device that is actually operated, the charging condition of the battery is variable at multiple ends, and the noise is high, so that the battery generally cannot be fully charged and discharged, and the sampling frequency of the data is relatively small compared with the aging cycle test, such as: the SOC interval is 30% -90%, and the sampling frequency is 10 seconds(s) or 30s to collect data once.

In this embodiment, in order to enable the first model to accurately predict the battery health state of the actually-operated electric device, the charging condition data of the second electric device may be counted to obtain the actual charging interval and the data sampling frequency of the actually-operated electric device.

Then, the aging cycle test data may be segmented by using an actual charging interval of the actually operated electric device to obtain first test data, and it is understood that the first test data only includes test data in the actual charging interval in the aging cycle test data. And re-sampling the first test data by using the data sampling frequency of the actually operated electric equipment to obtain second test data. Therefore, the charging interval and the data sampling frequency of the second test data can be kept consistent with those of the electric equipment which actually runs, and further the first model obtained by training the second test data can be used for accurately predicting the battery health state of the electric equipment which actually runs.

After the second test data is obtained, the second test data may be processed to obtain a second characteristic parameter, and the second characteristic parameter may be regarded as a health factor of the second battery. In order to improve the prediction reliability of the first model, the second characteristic parameter may include the same type of data as the first characteristic parameter determined based on the charge condition data of the first electromotive device.

Then, the second characteristic parameter may be used as an input of the first model, the calibrated maximum available capacity of the second battery may be used as an output of the first model, and the first model is trained until the first model converges, so as to obtain a trained first model. The trained first model is then used to predict the battery state of health of the electrically powered device in actual operation.

In this embodiment, the actual charging interval and the data sampling frequency of the target model battery are determined by using the charging condition data of the electrically-operated device which actually runs, and then the aging cycle test data of the second battery is processed by using the actual charging interval and the data sampling frequency to obtain second test data. The first model is then trained using a second characteristic parameter determined based on second test data, and a calibrated maximum available capacity of the second battery. Therefore, the first model can accurately predict the health state of the target type battery in the electric equipment which actually runs by utilizing the charging working condition data of the electric equipment which actually runs.

In some embodiments, the operating condition data of the first electric device is discharge condition data or standing condition data of the first electric device;

the first characteristic parameter comprises at least one of: an accumulated mileage of the first electrically powered device; an accumulated charge amount of the first battery; an accumulated discharge capacity of the first battery; the sum of the accumulated charge amount and the accumulated discharge amount of the first battery; a temperature of the first battery;

the target model is a second model, and the second model is obtained based on charging condition data of third electric equipment and training of the first model; the first model is obtained based on aging cycle test data of a second battery, charging condition data of second electric equipment and calibrated maximum available capacity training of the second battery; the first battery, the second battery, the battery of the second electric device and the battery of the third electric device are all target-type batteries.

In this embodiment, the first characteristic parameter is determined based on discharge condition data or rest condition data of the first electric device, and the first characteristic parameter may be regarded as an influence factor of the first battery.

The third electric device is an electric device for training the second model, and the third electric device is an electric device that actually operates.

Further, the battery of the third electrically powered device and the battery of the first electrically powered device may be the same model of battery, i.e., a target model of battery. In this way, the maximum available capacity of the first battery is predicted by using the charging condition data based on the third electric equipment and the second model obtained by training the first model, so that the reliability of acquiring the battery health state of the first battery can be improved.

The training of the second model is specifically described below.

acquiring operation condition data of the third electric equipment, wherein the operation condition data of the third electric equipment at least comprises charging condition data of the third electric equipment;

determining a third characteristic parameter and a fourth characteristic parameter according to the operating condition data of the third electric equipment;

inputting the third characteristic information into the first model to obtain a second maximum available capacity of a third battery, wherein the third battery is a battery of the third electric equipment;

training the second model according to the fourth characteristic parameter and the second maximum available capacity;

wherein the third characteristic parameter comprises at least one of: at least one charge voltage sample of the third battery; a slope of an open circuit voltage curve (e.g., SOC-OCV curve) of the third battery; a maximum value of a differential capacity curve of the third cell and a voltage corresponding to the maximum value; the starting time of the third time period is the time when the third battery is changed from constant-current charging to constant-voltage charging, and the ending time of the third time period is the time when the third battery is fully charged;

the fourth characteristic parameter comprises at least one of: an accumulated mileage of the third electrically powered device, an accumulated charge of the third battery, an accumulated discharge of the third battery, a sum of an accumulated charge and an accumulated discharge of the third battery, and a temperature of the third battery.

In this embodiment, the third characteristic parameter is determined based on the charging condition data of the third electric device, and the third characteristic parameter may be regarded as a battery of the third electric device, that is, a health factor of the third battery of the third electric device. In order to improve the prediction reliability of the second model, the third characteristic parameter may include the same type of data as the first characteristic parameter determined based on the charge condition data of the first electrically powered device.

Further, the operation condition data of the third electric device may further include discharge condition data or standing condition data of the third electric device.

The fourth characteristic parameter may be determined based on the discharge condition data or the standing condition data of the third electric device, or may be determined based on the data that the charge condition data, the discharge condition data, and the standing condition data of the third electric device all exist, and the fourth characteristic parameter may be regarded as an influence factor of the third battery. In order to improve the prediction reliability of the second model, the fourth characteristic parameter may include the same type of data as the first characteristic parameter determined based on the discharge condition data or the rest condition data of the first electric device.

In this embodiment, the third characteristic information may be input into the first model, and the current maximum available capacity of the third battery is obtained through prediction by the first model. And then, taking the fourth characteristic parameter as the input of the second model, taking the current maximum available capacity of the third battery as the output of the second model, and training the second model. Therefore, the second model can accurately predict the health state of the target type battery in the electric equipment in actual operation by utilizing the discharge working condition data or the standing working condition data of the electric equipment in actual operation.

It is to be understood that various alternative embodiments described in the embodiments of the present application may be implemented in combination with each other or separately without conflict between the embodiments, and the embodiments of the present application are not limited thereto.

In order to facilitate understanding of the battery state of health obtaining method provided in the embodiment of the present application, the battery state of health obtaining method is described below with a specific scenario embodiment.

In this scenario embodiment, the cloud platform may estimate the state of health of the battery by combining test data (data collected by an aging cycle test conducted in a laboratory) with actual operating condition data (data collected by a sensor of the electric device during actual operation). According to the situation that the actual working condition is different from the testing working condition, the testing data are processed by using the statistical result of the actual operation data, a machine learning model I (namely the first model) is constructed to achieve timely and accurate estimation of the health state of the battery in the actual charging process, and according to the situation that a large amount of charging data are missing in the cloud platform (privacy is not uploaded, power is not uploaded, and the like), a machine learning model II (namely the second model) is constructed to achieve health state estimation of all working conditions.

The method comprises the steps of carrying out statistical analysis on actual operation condition data received by a cloud platform, slicing and resampling (according to different SOC intervals, different sampling time intervals and the like) cycle test data through statistical results, extracting health factors (such as a voltage sequence, an SOC-OCV curve slope, a differential capacity curve peak position, a CCCV change point and the like) from the processed cycle data, describing a regression relation between the health factors and a calibration capacity (referring to the current rated capacity calibrated in an aging cycle test) through establishing a machine learning model I, and realizing timely and accurate estimation of the health state of the actual charging condition.

For the situation that charging data may not be uploaded in the practical application of the battery, influence factors existing in the charging and discharging working conditions are selected according to an electrochemical mechanism, such as: and (4) constructing a machine learning model II by the accumulated mileage of the electric equipment, the temperature of the battery and the like, and realizing the health state estimation of all working conditions.

According to the embodiment of the application, the accuracy of the test data is fully utilized, the variability of actual operation working conditions is fully considered, the health state of the battery in actual application under all working conditions is estimated accurately in time based on a machine learning method, and the problems that the calculable condition is few and the updating is not timely and inaccurate in the actual operation working conditions in the prior art can be effectively solved.

The overall concept of the embodiment of the present application is shown in fig. 2. Processing the cycle test data through the actual charging working condition, further extracting a health factor which can be calculated in the actual application, and constructing and training a machine learning model I to realize the health state estimation under the actual charging working condition; and extracting influence factors existing in all working conditions of practical application, constructing and training a machine learning model II, and realizing the health state estimation under all working conditions of practical application.

The specific implementation flow is shown in fig. 3. The method comprises the following steps:

s1, developing a battery aging test to obtain test data;

s2, acquiring battery data under the charging working condition of the real vehicle from the big data platform, and acquiring a statistical value of the working condition of the battery;

s3, carrying out multi-dimensional slicing and resampling on the test data according to the actual charging condition statistical value, and calculating and extracting the charging curve health characteristics;

s4, training a first model by using the characteristics of the step 3 and the standard maximum available capacity of the step 1 based on Xgboost, neural network and other regression machine learning;

s5, deploying and applying a model-big data platform, and carrying out timely and accurate maximum available capacity estimation on the battery with charging data;

s6, extracting battery data in the step 5, and training a machine learning model II of capacity throughput, accumulated mileage, temperature and the like and maximum available capacity;

and S7, deploying and applying a big data platform to realize timely and accurate estimation of the maximum available capacity of the battery without charging data uploading or charging data loss.

The embodiment of the application can achieve the following beneficial effects on the premise of not increasing the cost of software and hardware for products such as electric automobiles, electric two-wheeled vehicles and unmanned aerial vehicles which are deployed with cloud platforms: (1) The accuracy of the battery health state estimation result is improved; (2) And updating the health state estimation result of the mass battery of the cloud platform in real time.

Based on the method for acquiring the battery health status provided by the embodiment, correspondingly, the application further provides a specific implementation mode of the device for acquiring the battery health status. Please see the examples below.

Referring to fig. 4, a battery state of health obtaining apparatus provided in an embodiment of the present application may include:

the first receiving module 401 is configured to receive operation condition data of a first electric device, where the operation condition data of the first electric device includes at least one of charging condition data, discharging condition data, and standing condition data of the first electric device;

a first determining module 402, configured to determine a first characteristic parameter according to the operation condition data of the first electric device;

a first operation module 403, configured to input the first characteristic parameter into a target model matched with the first characteristic parameter, so as to obtain a first maximum available capacity of the first battery;

the first characteristic parameter comprises at least one of: at least one charge voltage sample of the first battery; a slope of an open circuit voltage curve of the first cell; a maximum value of a differential capacity curve of the first battery and a voltage corresponding to the maximum value; the starting time of the first time period is the time when the first battery is changed from constant-current charging to constant-voltage charging, and the ending time of the first time period is the time when the first battery is fully charged;

In some embodiments, the apparatus further comprises:

the first acquisition module is used for acquiring aging cycle test data of the second battery;

the second acquisition module is used for acquiring charging working condition data of the second electric equipment;

the statistical module is used for performing statistics on charging working condition data of the second electric equipment to obtain a statistical result, and the statistical result comprises an actual charging interval and data sampling frequency of the target type battery;

the segmentation module is used for segmenting the aging cycle test data according to the actual charging interval to obtain first test data;

the sampling module is used for resampling the first test data according to the data sampling frequency to obtain second test data;

a second determining module, configured to determine a second feature parameter according to the second test data, where the second feature parameter includes at least one of: at least one charge voltage sample of the second battery; a slope of an open circuit voltage curve (e.g., SOC-OCV curve) of the second battery; a maximum value of a differential capacity curve of the second battery and a voltage corresponding to the maximum value; the starting time of the second time period is the time when the second battery is changed from constant-current charging to constant-voltage charging, and the ending time of the second time period is the time when the second battery is fully charged;

and the first training module is used for training the first model according to the second characteristic parameter and the calibrated maximum available capacity of the second battery.

In some embodiments, the operation condition data of the first electric device is discharge condition data or standing condition data of the first electric device;

the first characteristic parameter comprises at least one of: an accumulated mileage of the first electrically powered device, an accumulated charge of the first battery, an accumulated discharge of the first battery, a sum of an accumulated charge and an accumulated discharge of the first battery, a temperature of the first battery;

In some embodiments, the apparatus further comprises:

the third acquisition module is used for acquiring the operating condition data of the third electric equipment, wherein the operating condition data of the third electric equipment at least comprises the charging condition data of the third electric equipment;

the third determining module is used for determining a third characteristic parameter and a fourth characteristic parameter according to the operating condition data of the third electric equipment;

a second operation module, configured to input the third feature information into the first model to obtain a second maximum available capacity of a third battery, where the third battery is a battery of the third electric device;

a second training module, configured to train the second model according to the fourth feature parameter and the second maximum available capacity;

wherein the third characteristic parameter comprises at least one of: at least one charge voltage sample of the third battery; a slope of an open circuit voltage curve (e.g., SOC-OCV curve) of the third battery; a maximum value of a differential capacity curve of the third cell and a voltage corresponding to the maximum value; the starting time of the third time period is the time when the third battery is changed from constant current charging to constant voltage charging, and the ending time of the third time period is the time when the third battery is fully charged;

the fourth characteristic parameter includes at least one of: an accumulated mileage of the third electrically powered device, an accumulated charge of the third battery, an accumulated discharge of the third battery, a sum of an accumulated charge and an accumulated discharge of the third battery, and a temperature of the third battery.

The battery health state acquiring device provided in the embodiment of the present application can implement each process implemented by the battery health state acquiring device in the method embodiment of fig. 1, and is not described here again to avoid repetition.

Fig. 5 shows a hardware structure diagram of battery state of health acquisition provided in an embodiment of the present application.

The battery state of health acquisition device may include a processor 501 and a memory 502 storing computer program instructions.

Specifically, the processor 501 may include a Central Processing Unit (CPU), or an Application Specific Integrated Circuit (ASIC), or may be configured to implement one or more Integrated circuits of the embodiments of the present Application.

Memory 502 may include mass storage for data or instructions. By way of example, and not limitation, memory 502 may include a Hard Disk Drive (HDD), a floppy Disk Drive, flash memory, an optical Disk, a magneto-optical Disk, tape, or a Universal Serial Bus (USB) Drive or a combination of two or more of these. Memory 502 may include removable or non-removable (or fixed) media, where appropriate. The memory 502 may be internal or external to the integrated gateway disaster recovery device, where appropriate. In a particular embodiment, the memory 502 is non-volatile solid-state memory.

The Memory may include Read-Only Memory (ROM), random Access Memory (RAM), magnetic disk storage media devices, optical storage media devices, flash Memory devices, electrical, optical, or other physical/tangible Memory storage devices. Thus, in general, the memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software comprising computer-executable instructions and when the software is executed (e.g., by one or more processors), it is operable to perform operations described with reference to the methods according to an aspect of the present disclosure.

The processor 501 reads and executes the computer program instructions stored in the memory 502 to implement any one of the battery state of health obtaining methods in the above embodiments.

In one example, the battery state of health acquisition device may also include a communication interface 503 and a bus 510. As shown in fig. 5, the processor 501, the memory 502, and the communication interface 503 are connected via a bus 510 to complete communication therebetween.

The communication interface 503 is mainly used for implementing communication between modules, apparatuses, units and/or devices in the embodiments of the present application.

Bus 510 includes hardware, software, or both to couple the components of the battery state of health acquisition device to each other. By way of example, and not limitation, a bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hypertransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an infiniband interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a video electronics standards association local (VLB) bus, or other suitable bus or a combination of two or more of these. Bus 510 may include one or more buses, where appropriate. Although specific buses are described and shown in the embodiments of the application, any suitable buses or interconnects are contemplated by the application.

In addition, in combination with the battery state of health obtaining method in the foregoing embodiments, the embodiments of the present application may provide a computer storage medium to implement. The computer storage medium having computer program instructions stored thereon; the computer program instructions, when executed by a processor, implement any of the battery state of health acquisition methods in the above embodiments.

It is to be understood that the present application is not limited to the particular arrangements and instrumentality described above and shown in the attached drawings. A detailed description of known methods is omitted herein for the sake of brevity. In the above embodiments, several specific steps are described and shown as examples. However, the method processes of the present application are not limited to the specific steps described and illustrated, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps, after comprehending the spirit of the present application.

The functional blocks shown in the above-described structural block diagrams may be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, it may be, for example, an electronic circuit, an Application Specific Integrated Circuit (ASIC), suitable firmware, plug-in, function card, or the like. When implemented in software, the elements of the present application are the programs or code segments used to perform the required tasks. The program or code segments may be stored in a machine-readable medium or transmitted by a data signal carried in a carrier wave over a transmission medium or a communication link. A "machine-readable medium" may include any medium that can store or transfer information. Examples of a machine-readable medium include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio Frequency (RF) links, and so forth. The code segments may be downloaded via computer networks such as the internet, intranet, etc.

It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, the present application is not limited to the order of the above steps, that is, the steps may be performed in the order mentioned in the embodiments, may be performed in an order different from the order in the embodiments, or may be performed at the same time.

Aspects of the present disclosure are described above with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the disclosure. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions/acts specified in the flowchart and/or block diagram block or blocks. Such a processor may be, but is not limited to, a general purpose processor, a special purpose processor, an application specific processor, or a field programmable logic circuit. It will also be understood that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based computer instructions which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

As described above, only the specific embodiments of the present application are provided, and it can be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working processes of the system, the module and the unit described above may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again. It should be understood that the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive various equivalent modifications or substitutions within the technical scope of the present application, and these modifications or substitutions should be covered within the scope of the present application.

Claims

1. A battery state of health obtaining method, comprising:

receiving operation condition data of first electric equipment, wherein the operation condition data of the first electric equipment comprises at least one of charging condition data, discharging condition data and standing condition data of the first electric equipment;

determining a first characteristic parameter according to the operation condition data of the first electric equipment;

inputting the first characteristic parameter into a target model matched with the first characteristic parameter to obtain a first maximum available capacity of a first battery;

2. The method of claim 1, wherein the operating condition data of the first electrically powered device comprises charging condition data of the first electrically powered device;

the first characteristic parameter comprises at least one of: at least one charge voltage sample of the first battery; a slope of an open circuit voltage curve of the first cell; a maximum value of a differential capacity curve of the first cell and a voltage corresponding to the maximum value; the starting time of the first time period is the time when the first battery is changed from constant-current charging to constant-voltage charging, and the ending time of the first time period is the time when the first battery is fully charged;

3. The method of claim 2, wherein before entering the first characteristic parameter into a target model matched to the first characteristic parameter to obtain the first maximum available capacity of the first battery, the method further comprises:

acquiring aging cycle test data of the second battery;

acquiring charging condition data of the second electric equipment;

determining a second characteristic parameter according to the second test data, wherein the second characteristic parameter comprises at least one of the following items: at least one charge voltage sample of the second battery; a slope of an open circuit voltage curve of the second cell; a maximum value of a differential capacity curve of the second battery and a voltage corresponding to the maximum value; the starting time of the second time period is the time when the second battery is changed from constant current charging to constant voltage charging, and the ending time of the second time period is the time when the second battery is fully charged;

4. The method according to any one of claims 1 to 3, characterized in that the operation condition data of the first electric device is discharge condition data or standing condition data of the first electric device;

5. The method of claim 4, wherein before entering the first characteristic parameter into a target model matched to the first characteristic parameter to obtain the first maximum available capacity of the first battery, the method further comprises:

determining a third characteristic parameter and a fourth characteristic parameter according to the operation condition data of the third electric equipment;

inputting the third characteristic information into the first model to obtain a second maximum available capacity of a third battery, wherein the third battery is a battery of the third electric device;

wherein the third characteristic parameter comprises at least one of: at least one charge voltage sample of the third battery; a slope of an open circuit voltage curve of the third cell; a maximum value of a differential capacity curve of the third battery and a voltage corresponding to the maximum value; the starting time of the third time period is the time when the third battery is changed from constant current charging to constant voltage charging, and the ending time of the third time period is the time when the third battery is fully charged;

the fourth characteristic parameter comprises at least one of: the accumulated mileage of the third electric equipment, the accumulated charge amount of the third battery, the accumulated discharge amount of the third battery, the sum of the accumulated charge amount and the accumulated discharge amount of the third battery, and the temperature of the third battery.

6. A battery state of health obtaining apparatus, comprising:

the first receiving module is used for receiving operation condition data of first electric equipment, wherein the operation condition data of the first electric equipment comprises at least one of charging condition data, discharging condition data and standing condition data of the first electric equipment;

the first determining module is used for determining a first characteristic parameter according to the operating condition data of the first electric equipment;

the first operation module is used for inputting the first characteristic parameter into a target model matched with the first characteristic parameter to obtain a first maximum available capacity of the first battery;

7. The apparatus of claim 6, wherein the operating condition data of the first electrically powered device comprises charging condition data of the first electrically powered device;

the target model is a first model obtained by training based on aging cycle test data of a second battery, charging condition data of second electric equipment and the calibrated maximum available capacity of the second battery, wherein the batteries of the first battery, the second battery and the second electric equipment are all target-type batteries.

8. The apparatus of claim 7, further comprising:

a second determining module, configured to determine a second feature parameter according to the second test data, where the second feature parameter includes at least one of: at least one charge voltage sample of the second battery; a slope of an open circuit voltage curve of the second cell; a maximum value of a differential capacity curve of the second battery and a voltage corresponding to the maximum value; the starting time of the second time period is the time when the second battery is changed from constant current charging to constant voltage charging, and the ending time of the second time period is the time when the second battery is fully charged;

9. The device according to any one of claims 6 to 8, wherein the operation condition data of the first electric equipment is discharge condition data or standing condition data of the first electric equipment;

the first characteristic parameter comprises at least one of: the accumulated mileage of the first electric equipment, the accumulated charge amount of the first battery, the accumulated discharge amount of the first battery, the sum of the accumulated charge amount and the accumulated discharge amount of the first battery, and the temperature of the first battery;

10. The apparatus of claim 9, further comprising:

the third determining module is used for determining a third characteristic parameter and a fourth characteristic parameter according to the operation condition data of the third electric equipment;

wherein the third characteristic parameter comprises at least one of: at least one charge voltage sample of the third battery; a slope of an open circuit voltage curve of the third cell; a maximum value of a differential capacity curve of the third cell and a voltage corresponding to the maximum value; the starting time of the third time period is the time when the third battery is changed from constant current charging to constant voltage charging, and the ending time of the third time period is the time when the third battery is fully charged;

11. A battery state of health acquiring device, characterized in that the device comprises: a processor and a memory storing computer program instructions; the processor, when executing the computer program instructions, implements the method of acquiring battery state of health as claimed in any one of claims 1 to 5.

12. A computer program product, wherein instructions in the computer program product, when executed by a processor of an electronic device, cause the electronic device to perform the method for obtaining battery state of health as claimed in any one of claims 1 to 5.