Battery-based data processing method, device, storage medium and electronic equipment

Abstract

The present invention discloses a battery-based data processing method, device, storage medium and electronic device, which relate to the field of batteries. The method comprises: obtaining the operating data of a target power source within a target time period to obtain power source data, wherein the type of the operating data comprises at least one of the following: voltage, current, temperature; obtaining the operating data of the battery within the target time period to obtain battery data, wherein the battery is deployed in the target power source; performing data fusion on the power source data and the battery data to obtain target fusion data; determining the health status of the battery based on the target fusion data and the target model; and adjusting the battery charge and discharge strategy when the health status of the battery indicates that the battery is in a faulty state. The present invention solves the technical problem in the related art that the operation and maintenance of the power source is performed based on the battery data in the power source, but the operation and maintenance effect is poor.

Description

Technical Field

[0001] The present invention relates to the field of batteries, and in particular to a battery-based data processing method, device, storage medium and electronic equipment. Background Art

[0002] In the related art, when operating and maintaining the power supply in the power system, the power supply monitoring system performs data analysis on the battery data in the power supply, and then operates and maintains the power supply based on the results of the data analysis. There is insufficient data analysis, which makes it impossible to accurately operate and maintain the power supply according to the power supply situation, affecting the battery life.

[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention

[0004] The embodiments of the present invention provide a battery-based data processing method, device, storage medium and electronic device to at least solve the technical problem in the related art that a power supply is operated and maintained based on battery data in the power supply, but the operation and maintenance effect is poor.

[0005] According to one aspect of an embodiment of the present invention, a battery-based data processing method is provided, including: acquiring operating data of a target power source within a target time period to obtain power source data, wherein the type of the operating data includes at least one of the following: voltage, current, and temperature; acquiring operating data of a battery within the target time period to obtain battery data, wherein the battery is deployed in the target power source; performing data fusion on the power source data and the battery data to obtain target fusion data; determining a health status of the battery based on the target fusion data and a target model, wherein the type of the target model includes: a machine learning model, and the health status of the battery includes one of the following: a normal state, a fault state; and adjusting a charge and discharge strategy of the battery when the health status of the battery indicates that the battery is in a fault state.

[0006] Further, the power supply data includes: the operating data of the target power supply at n moments, the battery data includes: the operating data of the battery at n moments, n is a positive integer, and the power supply data and the battery data are data-fused within the target time period at the n moments to obtain target fused data, including: data-fusion of the operating data of the target power supply at each moment and the operating data of the battery at that moment to obtain first fused data at each moment, wherein the first fused data at each moment includes at least one of the following: a first fused voltage obtained by fusing the voltage of the target power supply at that moment and the voltage of the battery at that moment, a first fused current obtained by fusing the current of the target power source at that moment and the current of the battery at that moment, and a first fused temperature obtained by fusing the temperature of the target power source at that moment and the temperature of the battery at that moment; performing data fusion on the first fused data at n said moments to obtain the target fused data, wherein the target fused data includes at least one of the following: a target fused voltage obtained by fusing the first fused voltages at n said moments, a target fused current obtained by fusing the first fused currents at n said moments, and a target fused temperature obtained by fusing the first fused temperatures at n said moments.

[0007] Further, data fusion is performed on the first fused data at n moments to obtain the target fused data, including: constructing an original sequence based on the first fused data at n moments, wherein the original sequence is used to record the first fused data at n moments; accumulating different numbers of first fused data in the original sequence respectively to obtain a target sequence; predicting the fused data at the target moment based on the target sequence to obtain second fused data, wherein the second fused data includes: fused data obtained by fusing the predicted operating data of the target power source at the target moment with the predicted operating data of the battery at the target moment, and the target moment is after the target time period; obtaining current fused data, wherein the current fused data includes: fused data obtained by fusing the operating data of the target power source at the current moment with the operating data of the battery at the current moment, and the current moment is after the target time period and before the target moment; performing weighted fusion on the second fused data and the current fused data to obtain the target fused data.

[0008] Further, the second fusion data includes at least one of the following: a second fused voltage obtained by fusing the predicted voltage of the target power supply at the target moment and the predicted voltage of the battery at the target moment, a second fused current obtained by fusing the predicted current of the target power supply at the target moment and the predicted current of the battery at the target moment, and a second fused temperature obtained by fusing the predicted temperature of the target power supply at the target moment and the predicted temperature of the battery at the target moment; the current fusion data includes: a current fused voltage obtained by fusing the voltage of the target power supply at the current moment and the voltage of the battery at the current moment, a current fused current obtained by fusing the current of the target power supply at the current moment and the current of the battery at the current moment, and the target The method comprises: calculating the absolute value of the difference between the second fusion data and the current fusion data to obtain an error value, wherein the error value comprises at least one of the following: the absolute value of the difference between the second fusion voltage and the current fusion voltage, the absolute value of the difference between the second fusion current and the current fusion current, and the absolute value of the difference between the second fusion temperature and the current fusion temperature; determining a preset weight based on the error value; and performing weighted fusion on the second fusion data and the current fusion data based on the preset weight to obtain the target fusion data.

[0009] Furthermore, based on the target fusion data and the target model, the health status of the battery is determined, including: calculating the change rate of the target fusion voltage and the current fusion voltage to obtain the voltage change rate; calculating the change rate of the target fusion current and the current fusion current to obtain the current change rate; calculating the change rate of the target fusion temperature and the current fusion temperature to obtain the temperature change rate; inputting the voltage change rate, the current change rate and the temperature change rate into the target model, and outputting the health status of the battery.

[0010] Furthermore, when the health status of the battery indicates that the battery is in a faulty state, the charge and discharge strategy of the battery is adjusted, including: determining the charge state of the battery at a current moment to obtain a current charge state; when the current charge state is less than a first preset threshold, prohibiting the battery from discharging; when the current charge state is greater than a second preset threshold, prohibiting the battery from charging, wherein the second preset threshold is greater than the first preset threshold.

[0011] Furthermore, in a case where the health status of the battery indicates that the battery is in a faulty state, the battery-based data processing method further includes: obtaining internal resistance data of the battery and current data of the battery, wherein the current data of the battery includes at least: a nominal current, and the internal resistance data of the battery includes at least: a battery internal resistance of the battery measured at the current moment; and adjusting the current size of the power supply and the battery based on the internal resistance data of the battery, the current data of the battery and a preset adjustment coefficient.

[0012] According to another aspect of an embodiment of the present invention, a battery-based data processing device is also provided, including: a first acquisition unit, used to acquire operating data of a target power source within a target time period to obtain power source data, wherein the type of the operating data includes at least one of the following: voltage, current, and temperature; a second acquisition unit, used to acquire operating data of the battery within the target time period to obtain battery data, wherein the battery is deployed in the target power source; a fusion unit, used to perform data fusion on the power source data and the battery data to obtain target fusion data; a determination unit, used to determine the health status of the battery based on the target fusion data and a target model, wherein the type of the target model includes: a machine learning model, and the health status of the battery includes one of the following: normal state, fault state; a first adjustment unit, used to adjust the charge and discharge strategy of the battery when the health status of the battery indicates that the battery is in a fault state.

[0013] Further, the power data includes: the operating data of the target power at n moments, where n is a positive integer; the battery data includes: the operating data of the battery at n moments, where the n moments are within the target time period; the fusion unit includes: a first fusion subunit, which is used to fuse the operating data of the target power at each moment with the operating data of the battery at that moment to obtain the first fused data at each moment, wherein the first fused data at each moment includes at least one of the following: a first fused voltage obtained by fusing the voltage of the target power at that moment with the voltage of the battery at that moment, a current of the target power at that moment; and the current of the battery at that moment and a first fusion current obtained by fusing the target power source at that moment and the temperature of the battery at that moment and a first fusion temperature obtained by fusing the target power source at that moment and the temperature of the battery at that moment; a second fusion subunit, used to perform data fusion on the first fusion data at n said moments to obtain the target fusion data, wherein the target fusion data includes at least one of the following: a target fusion voltage obtained by fusing the first fusion voltages at n said moments, a target fusion current obtained by fusing the first fusion currents at n said moments and a target fusion temperature obtained by fusing the first fusion temperatures at n said moments.

[0014] Further, the second fusion subunit includes: a construction module, which is used to construct an original sequence based on the first fusion data at n said moments, wherein the original sequence is used to record the first fusion data at n said moments; an accumulation module, which is used to accumulate different numbers of first fusion data in the original sequence respectively to obtain a target sequence; a prediction module, which is used to predict the fusion data at the target moment based on the target sequence to obtain second fusion data, wherein the second fusion data includes: fusion data obtained by fusing the predicted operation data of the target power supply at the target moment with the predicted operation data of the battery at the target moment, and the target moment is after the target time period; an acquisition module, which is used to acquire current fusion data, wherein the current fusion data includes: fusion data obtained by fusing the operation data of the target power supply at the current moment with the operation data of the battery at the current moment, and the current moment is after the target time period and before the target moment; a fusion module, which is used to perform weighted fusion on the second fusion data and the current fusion data to obtain the target fusion data.

[0015] Further, the second fusion data includes at least one of the following: a second fusion voltage obtained by fusing the predicted voltage of the target power supply at the target moment and the predicted voltage of the battery at the target moment, a second fusion current obtained by fusing the predicted current of the target power supply at the target moment and the predicted current of the battery at the target moment, and a second fusion temperature obtained by fusing the predicted temperature of the target power supply at the target moment and the predicted temperature of the battery at the target moment; the current fusion data includes: a current fusion voltage obtained by fusing the voltage of the target power supply at the current moment and the voltage of the battery at the current moment, a current fusion current obtained by fusing the current of the target power supply at the current moment and the current of the battery at the current moment, and and the current fusion temperature obtained by fusing the temperature of the target power supply at the current moment and the temperature of the battery at the current moment, the fusion module includes: a calculation submodule, used to calculate the absolute value of the difference between the second fusion data and the current fusion data, and obtain an error value, wherein the error value includes at least one of the following: the absolute value of the difference between the second fusion voltage and the current fusion voltage, the absolute value of the difference between the second fusion current and the current fusion current, and the absolute value of the difference between the second fusion temperature and the current fusion temperature; a determination submodule, used to determine a preset weight based on the error value; a fusion submodule, used to perform weighted fusion of the second fusion data and the current fusion data based on the preset weight to obtain the target fusion data.

[0016] Furthermore, the determination unit includes: a first calculation subunit, used to calculate the change rate of the target fusion voltage and the current fusion voltage to obtain the voltage change rate; a second calculation subunit, used to calculate the change rate of the target fusion current and the current fusion current to obtain the current change rate; a third calculation subunit, used to calculate the change rate of the target fusion temperature and the current fusion temperature to obtain the temperature change rate; a first processing subunit, used to input the voltage change rate, the current change rate and the temperature change rate into the target model, and output the health status of the battery.

[0017] Furthermore, the first adjustment unit includes: a determination subunit, used to determine the charge state of the battery at a current moment to obtain the current charge state; a second processing subunit, used to prohibit the battery from discharging when the current charge state is less than a first preset threshold; and a third processing subunit, used to prohibit the battery from charging when the current charge state is greater than a second preset threshold, wherein the second preset threshold is greater than the first preset threshold.

[0018] Furthermore, the battery-based data processing device also includes: a third acquisition unit, used to acquire the internal resistance data of the battery and the current data of the battery when the health status of the battery indicates that the battery is in a faulty state, wherein the current data of the battery at least includes: a nominal current, and the internal resistance data of the battery at least includes: a battery internal resistance of the battery measured at a current moment; a second adjustment unit, used to adjust the current size of the power supply and the battery based on the internal resistance data of the battery, the current data of the battery and a preset adjustment coefficient.

[0019] According to another aspect of an embodiment of the present invention, there is also provided an electronic device, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute any one of the above-mentioned battery-based data processing methods by executing the executable instructions.

[0020] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided, which stores a computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned battery-based data processing methods.

[0021] In the present invention, the operation data of the target power source in the target time period is obtained to obtain the power source data, wherein the type of the operation data includes at least one of the following: voltage, current, and temperature; the operation data of the battery in the target time period is obtained to obtain the battery data, wherein the battery is deployed in the target power source; the power source data and the battery data are data-fused to obtain the target fusion data; the health state of the battery is determined based on the target fusion data and the target model, wherein the type of the target model includes: a machine learning model, and the health state of the battery includes one of the following: a normal state and a fault state; when the health state of the battery indicates that the battery is in a fault state, the charge and discharge strategy of the battery is adjusted. Thus, the technical problem of poor operation and maintenance effect of the power source based on the battery data in the power source in the related art is solved. In the present invention, by data fusion of the operation data of the power source and the operation data of the battery in the power source, and based on the fused data, the health state of the battery is predicted by using the machine learning model, and the power source is operated and maintained according to the health state of the battery, the purpose of accurately operating and maintaining the power source according to the fused data to improve the battery life is achieved, thereby achieving the technical effect of improving the accuracy of the power source operation and maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0023] Figure 1 is a flow chart of an optional battery-based data processing method according to an embodiment of the present invention;

[0024] Figure 2 is a schematic diagram of an optional battery-based data processing device according to an embodiment of the present invention;

[0025] Figure 3 is a schematic diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0028] It should be noted that the user information (including but not limited to user device information, user personal information, etc.), collected information and data (including but not limited to data used for analysis, stored data, displayed data, battery data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data comply with the relevant laws, regulations and standards of the relevant regions, take necessary confidentiality measures, do not violate public order and good customs, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0029] Embodiment 1

[0030] According to an embodiment of the present invention, a method embodiment of an optional battery-based data processing method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0031] Figure 1 is a flow chart of an optional battery-based data processing method according to an embodiment of the present invention, such as Figure 1 As shown, the method comprises the following steps:

[0032] Step S101, acquiring operation data of a target power source within a target time period to obtain power source data, wherein the type of the operation data includes at least one of the following: voltage, current, and temperature.

[0033] The target power source may include a power source in a power communication or power system, and a battery, a rectifier, etc. may be deployed in the power source. The target time period may be a time period before the current moment. The type of the operation data may include at least one of the following: voltage, current, temperature, internal resistance, and capacity, etc.

[0034] In this embodiment, the operating data of the target power source at n moments in the target time period may be collected to obtain the above power source data.

[0035] Step S102, acquiring operation data of the battery in a target time period to obtain battery data, wherein the battery is deployed in a target power source.

[0036] The above-mentioned battery may include but is not limited to a storage battery deployed in the target power supply. In this embodiment, the above-mentioned battery data can be obtained based on the capacity data of the battery capacity control device. For example, the battery operation data can be collected by the capacity control device (or capacity control device) to obtain the above-mentioned battery data.

[0037] It should be noted that, in an optional example, the collected power data and battery data may also be preprocessed, for example, by denoising, filtering and normalization, wherein Kalman filtering may be used for filtering, and normalization may be used to eliminate the influence of dimensions.

[0038] Assume that the collected battery data (voltage, current, temperature, internal resistance, capacity, etc.) are as shown in Table 1:

[0039] Table 1

[0040]

[0041] When denoising battery data, the moving average method can be used to eliminate noise. Assuming that the voltage data is noisy, the denoising formula can be:

[0042]

[0043] For example, t represents time, represents the voltage after denoising. If n=3, the voltage data at time t2 can be:

[0044]

[0045] Step S103, performing data fusion on the power source data and the battery data to obtain target fused data.

[0046] In this embodiment, the power data and the capacitance data can be fused. For example, the voltage of the target power supply and the voltage of the battery can be fused, the current of the target power supply and the current of the battery can be fused, and the temperature of the target power supply and the temperature of the battery can be fused to obtain target fusion data.

[0047] Step S104, determining the health status of the battery based on the target fusion data and the target model, wherein the type of the target model includes: a machine learning model, and the health status of the battery includes one of the following: a normal state, a fault state.

[0048] The type of the above-mentioned target model can be a machine learning model. For example, the target model can be an SVM (Support Vector Machine). The target model can include: performing data fusion on the operating data of a specified power source within a historical time period and the operating data of a battery within the specified power source within a historical time period to obtain historical fused data, wherein the historical fused data can include: fused voltage, fused current, and fused temperature, etc. The historical time period can be before the target time period. Then, based on the historical fused data and the health status of the battery within the historical time period, the support vector machine to be trained can be trained to obtain the target model.

[0049] Based on the historical fusion data and the health status of the battery in the historical time, the support vector machine to be trained is trained to obtain the target model, which may include: based on the historical fusion data, calculating the change rate of the fused voltage, the change rate of the fused current and the change rate of the fused temperature, and then using the change rate of the fused voltage, the change rate of the fused current and the change rate of the fused temperature as training samples, and using the health status of the battery corresponding to the historical fusion data as the training label, and inputting the support vector machine to be trained for model training to obtain a model that can predict the health status of the battery.

[0050] In this embodiment, the health state of the battery can be evaluated based on the target fusion data using the target model. The health state of the battery can be a normal state or a fault state, wherein the normal state can be represented as the battery being in a non-fault state.

[0051] Step S105 , when the battery health status indicates that the battery is in a fault state, adjusting the battery charge and discharge strategy.

[0052] When the battery health status indicates that the battery is in a faulty state, the battery charge and discharge strategy can be adjusted. When the battery health status indicates that the battery is in a normal state, the battery charge and discharge strategy does not need to be adjusted and the current charge and discharge strategy remains unchanged.

[0053] Through the above steps, in this embodiment, by performing data fusion on the operating data of the power supply and the operating data of the battery in the power supply, and based on the fused data, using a machine learning model to predict the health status of the battery, the power supply is operated and maintained according to the health status of the battery, thereby achieving the purpose of accurately operating and maintaining the power supply according to the fused data to increase the battery life, thereby achieving the technical effect of improving the accuracy of power supply operation and maintenance, and further solving the technical problem in the related art of operating and maintaining the power supply based on the battery data in the power supply, but with poor operation and maintenance effect.

[0054] Optionally, the power supply data includes: operating data of the target power supply at n moments, where n is a positive integer, and the battery data includes: operating data of the battery at n moments, and the power supply data and the battery data are data-fused at the n moments within the target time period to obtain target fused data, including: data-fusion of the operating data of the target power supply at each moment and the operating data of the battery at that moment to obtain first fused data at each moment, wherein the first fused data at each moment includes at least one of the following: a first fused voltage obtained by fusing the voltage of the target power supply at that moment and the voltage of the battery at that moment, a first fused current obtained by fusing the current of the target power supply at that moment and the current of the battery at that moment, and a first fused temperature obtained by fusing the temperature of the target power supply at that moment and the temperature of the battery at that moment; data fusion of the first fused data at n moments to obtain target fused data, wherein the target fused data includes at least one of the following: a target fused voltage obtained by fusing the first fused voltages at n moments, a target fused current obtained by fusing the first fused currents at n moments, and a target fused temperature obtained by fusing the first fused temperatures at n moments.

[0055] The power source data may include: operating data of the target power source at n moments, and the battery data may include: operating data of the battery at n moments, where the n moments are within the target time period, and n may be a positive integer.

[0056] In this embodiment, the operating data of the target power source at n moments and the operating data of the battery at n moments may also be aligned to ensure that data from different sources correspond to the same time point.

[0057] In this embodiment, the operating data of the target power supply at each moment and the operating data of the battery at that moment can be fused to obtain first fused data at each moment, wherein the first fused data at each moment includes at least one of the following: a first fused voltage obtained by fusing the voltage of the target power supply at that moment and the voltage of the battery at that moment, a first fused current obtained by fusing the current of the target power supply at that moment and the current of the battery at that moment, and a first fused temperature obtained by fusing the temperature of the target power supply at that moment and the temperature of the battery at that moment.

[0058] When fusing the operating data of the target power supply at each moment and the operating data of the battery at that moment, a weighted summation method can be used for data fusion. For example, a first fused voltage can be obtained by weighted summing the voltage of the target power supply at each moment and the voltage of the battery at that moment, a first fused current can be obtained by weighted summing the current of the target power supply at each moment and the current of the battery at that moment, and a first fused temperature can be obtained by weighted summing the temperature of the target power supply at each moment and the temperature of the battery at that moment.

[0059] In this embodiment, after obtaining the first fused data at each moment, the first fused data at n moments can also be fused to obtain target fused data. For example, based on the first fused data at n moments, a gray prediction model (such as a gray model) can be used to predict the fused data at the target moment (for example, the predicted target moment target power supply operation data and the predicted target moment battery operation data are fused to obtain data), and then the target moment fused data and the current fused data (for example, the current moment target power supply operation data and the current moment battery operation data are fused to obtain data) are fused to obtain target fused data. This avoids the situation where the data used to guide the operation of the power supply is inaccurate, resulting in the inability to accurately operate and maintain the power supply.

[0060] Optionally, data fusion is performed on the first fused data at n moments to obtain target fused data, including: constructing an original sequence based on the first fused data at n moments, wherein the original sequence is used to record the first fused data at n moments; accumulating different numbers of first fused data in the original sequence respectively to obtain a target sequence; predicting the fused data at the target moment based on the target sequence to obtain second fused data, wherein the second fused data includes: fused data obtained by fusing the predicted operating data of the target power source at the target moment with the predicted operating data of the battery at the target moment, the target moment being after the target time period; obtaining current fused data, wherein the current fused data includes: fused data obtained by fusing the operating data of the target power source at the current moment with the operating data of the battery at the current moment, the current moment being after the target time period and the current moment being before the target moment; weighted fusion is performed on the second fused data and the current fused data to obtain target fused data.

[0061] For example, in this embodiment, the above-mentioned original sequence can be composed of the first fused data at n moments, and each first fused data in the original sequence can be accumulated with the first fused data before it to obtain the target sequence, and then a differential equation can be constructed based on the target sequence, wherein the differential equation includes parameters to be solved, and then the parameter value of the parameter to be solved can be solved by the least squares method; then the fused data at the target moment is predicted according to the parameter value to obtain the second fused data, and after obtaining the second fused data, the second fused data and the current fused data can be fused by weighted summation to obtain the target fused data.

[0062] For example, data fusion is performed on the first fusion data at n moments to obtain the target fusion data, which may include: (1) original sequence: assuming that the voltage or other key data sequence is (corresponding to the original sequence), where can represent the first fusion data at the nth moment. (2) Accumulated generated sequence: The generated sequence can be expressed as (corresponding to the target sequence), where , where k represents any data from 1 to n. (3) Model construction: The difference equation can be constructed using the cumulative generation sequence , and then solve for the parameters and . (4) Prediction: The value at the next moment can be predicted based on the grey prediction model (corresponding to the fused data at the target moment). (5) Data fusion: The value at the current moment (corresponding to the current fused data) and the predicted value at the next moment are fused to obtain the target fused data.

[0063] The following takes the first fusion data at each moment as the first fusion voltage obtained by fusing the voltage of the target power supply at that moment and the voltage of the battery at that moment as an example for explanation:

[0064] (1) Construct the original sequence: Assume that at time arrive Collected between Voltage data (ie n first fusion voltages).

[0065] (2) Accumulate and generate the sequence y(k):

[0066]

[0067] (3) Construct the difference equation:

[0068]

[0069] Among them, a and b are the parameters to be solved, t is the time, and d is the differential symbol.

[0070] Solve for parameters using the least squares method and .

[0071] (4) Predict the voltage at the next moment :

[0072]

[0073] in, is the initial data.

[0074] Assume that at time The collected data are as follows:

[0075] Voltage V (volts); current A (ampere); temperature (Celsius); Internal resistance Ω (Ohm).

[0076] Grey prediction models can be established, including:

[0077] Assume that the data at the past moment is: V (volts);

[0078] The cumulative generated sequence can be: V;

[0079] Solving Parameters and :Use the least squares method to solve , ;

[0080] The predicted voltage at the next moment is: .

[0081] In this embodiment, the grey prediction model can be used to make accurate short-term predictions of the power system when processing small amounts of data and nonlinear data, with low computational complexity and the ability to quickly respond to changes in real-time data.

[0082] Optionally, the second fusion data includes at least one of the following: a second fusion voltage obtained by fusing the predicted voltage of the target power supply at the target moment and the predicted voltage of the battery at the target moment, a second fusion current obtained by fusing the predicted current of the target power supply at the target moment and the predicted current of the battery at the target moment, and a second fusion temperature obtained by fusing the predicted temperature of the target power supply at the target moment and the predicted temperature of the battery at the target moment. The current fusion data includes: a current fusion voltage obtained by fusing the voltage of the target power supply at the current moment and the voltage of the battery at the current moment, a current fusion current obtained by fusing the current of the target power supply at the current moment and the current of the battery at the current moment. and the current fusion temperature obtained by fusing the temperature of the target power supply at the current moment and the temperature of the battery at the current moment, weightedly fusing the second fusion data and the current fusion data to obtain the target fusion data, including: calculating the absolute value of the difference between the second fusion data and the current fusion data to obtain an error value, wherein the error value includes at least one of the following: the absolute value of the difference between the second fusion voltage and the current fusion voltage, the absolute value of the difference between the second fusion current and the current fusion current, and the absolute value of the difference between the second fusion temperature and the current fusion temperature; based on the error value, determining a preset weight; based on the preset weight, weightedly fusing the second fusion data and the current fusion data to obtain the target fusion data.

[0083] The following example illustrates the process of weighted fusion of the second fusion data and the current fusion data to obtain the target fusion data, taking the second fusion data as the second fusion voltage and the current fusion data as the current fusion voltage. It should be noted that the weighted fusion of the second fusion current and the current fusion current and the weighted fusion of the second fusion temperature and the current fusion temperature are based on the same principle as the weighted fusion of the second fusion voltage and the current fusion voltage, and will not be elaborated here.

[0084] Fusion of the currently measured voltage (corresponding to the current fusion voltage) and the predicted value (corresponding to the second fusion voltage), the formula used is:

[0085]

[0086] in, It can represent the target fusion voltage, Can represent preset weights.

[0087] Preset Weights According to the prediction error (corresponding to the error value) is dynamically adjusted, where the prediction error The calculation formula is:

[0088]

[0089] The preset weight can also be adjusted according to the error. The formula for adjusting the preset weight can be:

[0090]

[0091] Among them, λ is a preset value.

[0092] For example, =12.4V, =12.38, λ=5 is taken as an example:

[0093] Calculate the error value: V.

[0094] Calculate preset weights: .

[0095] The calculation formula for the fused voltage (corresponding to the target fused voltage) is:

[0096] V

[0097] By fusing the current measured voltage (corresponding to the current fusion voltage) and the predicted value , to avoid the situation in which the data analysis of the power supply in related technologies is insufficient, making it difficult to accurately operate and maintain the power supply.

[0098] Optionally, based on the target fusion data and the target model, the health state of the battery is determined, including: calculating the rate of change of the target fusion voltage and the current fusion voltage to obtain the voltage change rate; calculating the rate of change of the target fusion current and the current fusion current to obtain the current change rate; calculating the rate of change of the target fusion temperature and the current fusion temperature to obtain the temperature change rate; inputting the voltage change rate, the current change rate and the temperature change rate into the target model, and outputting the health state of the battery.

[0099] For example, the formula for calculating the voltage change rate can be:

[0100]

[0101] Among them, Voltage Change Rate can represent the voltage change rate, V(t) can represent the fusion voltage at time point t (corresponding to the target fusion voltage), and V(t-1) can represent the fusion voltage at time point t-1 (corresponding to the current fusion voltage).

[0102] For time point t2, if V(t)=12.4V, V(t-1)=12.4V, then the voltage change rate at time point t2 is:

[0103]

[0104] It should be noted that the calculation principles of the current change rate, the temperature change rate and the voltage change rate are the same and will not be elaborated here.

[0105] In this embodiment, the voltage change rate, current change rate and temperature change rate can be input into the target model to output the health status of the battery. It should be noted that, in an optional example, the health status of the battery can be predicted by using a machine learning model based on only at least one of the voltage change rate, current change rate, temperature change rate and internal resistance change rate. At this time, the training samples of the machine learning model can be adjusted adaptively, wherein the calculation formula of the internal resistance change rate is similar to the voltage change rate, and the calculation formula of the internal resistance change rate can be:

[0106]

[0107] Among them, Resistance Change Rate can represent the internal resistance change rate, R(t) can represent the internal resistance at time point t, and R(t-1) can represent the internal resistance at time point t-1.

[0108] In this embodiment, the voltage change rate, current change rate and temperature change rate can be input into the target model. Assuming that the model prediction result is 1 (failure is about to occur), the system will adjust the charging and discharging strategy, such as reducing the charging current or stopping discharging, to extend the battery life, thereby achieving the purpose of precise operation and maintenance of the power supply.

[0109] Optionally, when the battery health status indicates that the battery is in a fault state, the battery charge and discharge strategy is adjusted, including: determining the charge state of the battery at the current moment to obtain the current charge state; when the current charge state is less than a first preset threshold, prohibiting the battery from discharging; when the current charge state is greater than a second preset threshold, prohibiting the battery from charging, wherein the second preset threshold is greater than the first preset threshold.

[0110] In this embodiment, the dynamic SOC (state of charge) of the battery can be calculated using the following formula:

[0111]

[0112] Among them, Q nom It can represent the nominal capacity of the battery, and SOC0 can represent the state of charge of the battery obtained at a certain time t0 before the current time. It can represent the current moment, and I(t) is the instantaneous current at time point t. If the current is a charging current, the SOC can be increased; if it is a discharging current, the SOC can be reduced.

[0113] In this embodiment, a preset threshold of the charge and discharge strategy can also be set. When SOC(t) > SOCmax (corresponding to the second preset threshold), charging is stopped. When SOC(t) < SOCmin (corresponding to the first preset threshold), discharging is stopped, achieving the purpose of adjusting the charge and discharge strategy according to the battery state to extend the battery life.

[0114] Optionally, in the case where the health state of the battery indicates that the battery is in a faulty state, the data processing method based on the battery further includes: obtaining the internal resistance data of the battery and the current data of the battery. Among them, the current data of the battery at least includes: the nominal current, and the internal resistance data of the battery at least includes: the internal resistance of the battery measured at the current moment; based on the internal resistance data of the battery, the current data of the battery, and a preset adjustment coefficient, the current magnitudes of the power supply and the battery are adjusted.

[0115] In this embodiment, according to the current state of the battery and the predicted battery life, the battery life can be extended or the efficiency can be improved by adjusting the charging current Icharge and the discharging current Idischarge. In this embodiment, the fault prediction result can be utilized. For example, if the health state of the battery indicates that the battery is in a faulty state, the current magnitude can be adjusted. The increase in the internal resistance of the battery indicates battery aging, and the current magnitude can also be adjusted. The calculation formula for adjusting the current magnitude can be:

[0116]

[0117] where, I adjust can represent the adjusted current, I nom can represent the nominal current (for example, the current value marked on the electrical appliance or electronic device), R measured can represent the currently measured internal resistance of the battery, R nom is the nominal internal resistance of the battery (i.e., the internal resistance measured when the battery is in the standard state), and k is an adjustment coefficient.

[0118] In actual operation, the calculation and adjustment of the current and the charge and discharge strategy can be carried out in an iterative manner, continuously optimizing the charge and discharge strategy to achieve the best battery life and system performance.

[0119] Assume: Initial SOC: SOC0 = 0.5 (i.e., 50%), nominal capacity: Q nom = 100 Ah, the current charging current is: I charge = 10 A, the currently measured internal resistance of the battery is: R measured = 0.02 Ω, the nominal internal resistance is: R nom = 0.015 Ω, k = 0.5.

[0120] The adjusted charging current can be:

[0121]

[0122] At this time, the adjusted charging power can be:

[0123]

[0124] By dynamically adjusting the charge and discharge current, the battery efficiency can be optimized and its service life can be extended.

[0125] In this embodiment, by fusing the operating data of the power supply and the operating data of the battery in the power supply, and based on the fused data, using a machine learning model to predict the health status of the battery, the power supply is operated and maintained according to the health status of the battery, thereby achieving the purpose of accurately operating and maintaining the power supply based on the fused data to increase the battery life, thereby achieving the technical effect of improving the accuracy of power supply operation and maintenance, and further solving the technical problem in the related art of operating and maintaining the power supply based on the battery data in the power supply, but with poor operation and maintenance effect.

[0126] Embodiment 2

[0127] The second embodiment of the present invention provides an optional battery-based data processing device, and each implementation unit in the data processing device corresponds to each implementation step in the first embodiment.

[0128] Figure 2 is a schematic diagram of an optional battery-based data processing device according to an embodiment of the present invention, such as Figure 2 As shown, it includes: a first acquisition unit 21, a second acquisition unit 22, a fusion unit 23, a determination unit 24 and a first adjustment unit 25.

[0129] A first acquisition unit 21 is used to acquire operating data of a target power source within a target time period to obtain power source data, wherein the type of the operating data includes at least one of the following: voltage, current, and temperature;

[0130] A second acquisition unit 22 is used to acquire operation data of the battery within a target time period to obtain battery data, wherein the battery is deployed in a target power source;

[0131] A fusion unit 23 is used to fuse the power data and the battery data to obtain target fusion data;

[0132] A determination unit 24 is used to determine the health state of the battery based on the target fusion data and the target model, wherein the type of the target model includes: a machine learning model, and the health state of the battery includes one of the following: a normal state and a fault state;

[0133] The first adjustment unit 25 is used to adjust the charge and discharge strategy of the battery when the health status of the battery indicates that the battery is in a fault state.

[0134] In the battery-based data processing device provided in the second embodiment of the present invention, the first acquisition unit 21 can be used to acquire the operating data of the target power source in the target time period to obtain power source data, wherein the type of the operating data includes at least one of the following: voltage, current, and temperature; the second acquisition unit 22 can be used to acquire the operating data of the battery in the target time period to obtain battery data, wherein the battery is deployed in the target power source; the fusion unit 23 performs data fusion on the power source data and the battery data to obtain target fusion data; the determination unit 24 determines the health state of the battery based on the target fusion data and the target model, wherein the type of the target model includes: a machine learning model; the health state of the battery includes one of the following: a normal state and a fault state; the first adjustment unit 25 adjusts the battery charging and discharging strategy when the health state of the battery indicates that the battery is in a fault state. This solves the technical problem of poor operation and maintenance effect of the power source based on the battery data in the power source in the related art. In this embodiment, by fusing the operating data of the power supply and the operating data of the battery in the power supply, and based on the fused data, using a machine learning model to predict the health status of the battery, the power supply is operated and maintained according to the health status of the battery, thereby achieving the purpose of accurately operating and maintaining the power supply based on the fused data to increase the battery life, thereby achieving the technical effect of improving the accuracy of power supply operation and maintenance.

[0135] Optionally, in the battery-based data processing device provided in the second embodiment of the present invention, the power data includes: the operating data of the target power at n moments, n is a positive integer, the battery data includes: the operating data of the battery at n moments, the n moments are within the target time period, and the fusion unit includes: a first fusion subunit, which is used to perform data fusion on the operating data of the target power at each moment and the operating data of the battery at that moment to obtain first fusion data at each moment, wherein the first fusion data at each moment includes at least one of the following: a first fusion voltage obtained by fusion between the voltage of the target power at that moment and the voltage of the battery at that moment, a first fusion current obtained by fusion between the current of the target power at that moment and the current of the battery at that moment, and a first fusion temperature obtained by fusion between the temperature of the target power at that moment and the temperature of the battery at that moment; a second fusion subunit, which is used to perform data fusion on the first fusion data at n moments to obtain target fusion data, wherein the target fusion data includes at least one of the following: a target fusion voltage obtained by fusion of the first fusion voltages at n moments, a target fusion current obtained by fusion of the first fusion currents at n moments, and a target fusion temperature obtained by fusion of the first fusion temperatures at n moments.

[0136] Optionally, in the battery-based data processing device provided in the second embodiment of the present invention, the second fusion subunit includes: a construction module, which is used to construct an original sequence based on the first fusion data at n moments, wherein the original sequence is used to record the first fusion data at n moments; an accumulation module, which is used to accumulate different numbers of first fusion data in the original sequence respectively to obtain a target sequence; a prediction module, which is used to predict the fusion data at the target moment based on the target sequence to obtain second fusion data, wherein the second fusion data includes: fusion data obtained by fusing the predicted operation data of the target power supply at the target moment with the predicted operation data of the battery at the target moment, and the target moment is after the target time period; an acquisition module, which is used to acquire current fusion data, wherein the current fusion data includes: fusion data obtained by fusing the operation data of the target power supply at the current moment with the operation data of the battery at the current moment, and the current moment is after the target time period and before the target moment; a fusion module, which is used to perform weighted fusion on the second fusion data and the current fusion data to obtain target fusion data.

[0137] Optionally, in the battery-based data processing device provided in the second embodiment of the present invention, the second fused data includes at least one of the following: a second fused voltage obtained by fusing the predicted voltage of the target power supply at the target moment and the predicted voltage of the battery at the target moment, a second fused current obtained by fusing the predicted current of the target power supply at the target moment and the predicted current of the battery at the target moment, and a second fused temperature obtained by fusing the predicted temperature of the target power supply at the target moment and the predicted temperature of the battery at the target moment, and the current fused data includes: a current fused voltage obtained by fusing the voltage of the target power supply at the current moment and the voltage of the battery at the current moment, a second fused current obtained by fusing the predicted current of the target power supply at the target moment and the predicted temperature of the battery at the target moment. The current fusion current obtained after fusion and the temperature of the target power supply at the current moment and the temperature of the battery at the current moment are fused to obtain the current fusion temperature. The fusion module includes: a calculation submodule, used to calculate the absolute value of the difference between the second fusion data and the current fusion data to obtain an error value, wherein the error value includes at least one of the following: the absolute value of the difference between the second fusion voltage and the current fusion voltage, the absolute value of the difference between the second fusion current and the current fusion current, and the absolute value of the difference between the second fusion temperature and the current fusion temperature; a determination submodule, used to determine a preset weight based on the error value; a fusion submodule, used to perform weighted fusion on the second fusion data and the current fusion data based on the preset weight to obtain target fusion data.

[0138] Optionally, in the battery-based data processing device provided in Embodiment 2 of the present invention, the determination unit includes: a first calculation subunit, used to calculate the rate of change of the target fusion voltage and the current fusion voltage, and obtain the voltage change rate; a second calculation subunit, used to calculate the rate of change of the target fusion current and the current fusion current, and obtain the current change rate; a third calculation subunit, used to calculate the rate of change of the target fusion temperature and the current fusion temperature, and obtain the temperature change rate; a first processing subunit, used to input the voltage change rate, the current change rate and the temperature change rate into the target model, and output the health status of the battery.

[0139] Optionally, in the battery-based data processing device provided in Embodiment 2 of the present invention, the first adjustment unit includes: a determination subunit, used to determine the charge state of the battery at a current moment to obtain the current charge state; a second processing subunit, used to prohibit the battery from discharging when the current charge state is less than a first preset threshold; and a third processing subunit, used to prohibit the battery from charging when the current charge state is greater than a second preset threshold, wherein the second preset threshold is greater than the first preset threshold.

[0140] Optionally, in the battery-based data processing device provided in Embodiment 2 of the present invention, the battery-based data processing device also includes: a third acquisition unit, used to acquire the internal resistance data of the battery and the current data of the battery when the battery health status indicates that the battery is in a fault state, wherein the battery current data at least includes: the nominal current, and the battery internal resistance data at least includes: the battery internal resistance of the battery measured at the current moment; a second adjustment unit, used to adjust the current size of the power supply and the battery based on the battery internal resistance data, the battery current data and a preset adjustment coefficient.

[0141] The above-mentioned battery-based data processing device may also include a processor and a memory. The above-mentioned first acquisition unit 21, second acquisition unit 22, fusion unit 23, determination unit 24 and first adjustment unit 25 are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to realize corresponding functions.

[0142] The above processor includes a kernel, and the kernel retrieves the corresponding program unit from the memory. One or more kernels can be set, and the operating data of the power supply and the operating data of the battery in the power supply are fused by adjusting the kernel parameters, and based on the fused data, the health status of the battery is predicted using a machine learning model, and the power supply is operated and maintained according to the health status of the battery, so as to achieve the purpose of accurately operating and maintaining the power supply according to the fused data to improve the battery life, thereby achieving the technical effect of improving the accuracy of power supply operation and maintenance.

[0143] The above-mentioned memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one storage chip.

[0144] According to another aspect of an embodiment of the present invention, there is also provided an electronic device, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to execute any one of the above-mentioned battery-based data processing methods by executing the executable instructions.

[0145] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided, which stores a computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute any one of the above-mentioned battery-based data processing methods.

[0146] Figure 3 is a schematic diagram of an electronic device according to an embodiment of the present invention, such as Figure 3 As shown, an embodiment of the present invention provides an electronic device 30, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, any one of the above-mentioned battery-based data processing methods is implemented.

[0147] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0148] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0149] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0150] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0151] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0152] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk, etc. Various media that can store program codes.

[0153] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A battery-based data processing method, characterized in that: include: Acquire operation data of a target power source within a target time period to obtain power source data, wherein the type of the operation data includes at least one of the following: voltage, current, and temperature; Acquire operation data of a battery within the target time period to obtain battery data, wherein the battery is deployed in the target power source; Performing data fusion on the power source data and the battery data to obtain target fusion data; Determine the health state of the battery based on the target fusion data and the target model, wherein the type of the target model includes: a machine learning model, and the health state of the battery includes one of the following: a normal state and a fault state; When the health status of the battery indicates that the battery is in a fault state, adjusting a charge and discharge strategy of the battery; The power supply data includes: the operating data of the target power supply at n moments, where n is a positive integer; the battery data includes: the operating data of the battery at n moments, and the power supply data and the battery data are fused within the target time period at the n moments to obtain target fused data, including: fusing the operating data of the target power supply at each moment with the operating data of the battery at that moment to obtain first fused data at each moment, wherein the first fused data at each moment includes at least one of the following: a first fused voltage obtained by fusing the voltage of the target power supply at that moment with the voltage of the battery at that moment, a first fused current obtained by fusing the current of the target power source at that moment and the current of the battery at that moment, and a first fused temperature obtained by fusing the temperature of the target power source at that moment and the temperature of the battery at that moment; fusing the first fused data at n moments to obtain the target fused data, wherein the target fused data includes at least one of the following: a target fused voltage obtained by fusing the first fused voltages at n moments, a target fused current obtained by fusing the first fused currents at n moments, and a target fused temperature obtained by fusing the first fused temperatures at n moments; Performing data fusion on the first fusion data at n moments to obtain the target fusion data, including: constructing an original sequence based on the first fusion data at n moments, wherein the original sequence is used to record the first fusion data at n moments; accumulating different numbers of first fusion data in the original sequence respectively to obtain a target sequence; predicting the fusion data at the target moment based on the target sequence to obtain second fusion data, wherein the second fusion data includes: fusion data obtained by fusing the predicted operation data of the target power source at the target moment with the predicted operation data of the battery at the target moment, and the target moment is after the target time period; acquiring current fusion data, wherein the current fusion data includes: fusion data obtained by fusing the operation data of the target power source at the current moment with the operation data of the battery at the current moment, and the current moment is after the target time period and before the target moment; performing weighted fusion on the second fusion data and the current fusion data to obtain the target fusion data.

2. The battery-based data processing method according to claim 1, characterized in that: The second fusion data includes at least one of the following: a second fused voltage obtained by fusing the predicted voltage of the target power supply at the target moment and the predicted voltage of the battery at the target moment, a second fused current obtained by fusing the predicted current of the target power supply at the target moment and the predicted current of the battery at the target moment, and a second fused temperature obtained by fusing the predicted temperature of the target power supply at the target moment and the predicted temperature of the battery at the target moment; the current fusion data includes: a current fused voltage obtained by fusing the voltage of the target power supply at the current moment and the voltage of the battery at the current moment, a current fused current obtained by fusing the current of the target power supply at the current moment and the current of the battery at the current moment, and a current fused temperature obtained by fusing the temperature of the target power supply at the current moment and the temperature of the battery at the current moment, Performing weighted fusion on the second fused data and the current fused data to obtain the target fused data includes: Calculating an absolute value of a difference between the second fusion data and the current fusion data to obtain an error value, wherein the error value includes at least one of the following: an absolute value of a difference between the second fusion voltage and the current fusion voltage, an absolute value of a difference between the second fusion current and the current fusion current, and an absolute value of a difference between the second fusion temperature and the current fusion temperature; Based on the error value, determining a preset weight; Based on the preset weight, the second fused data and the current fused data are weightedly fused to obtain the target fused data.

3. The battery-based data processing method according to claim 2, characterized in that: Determining the health state of the battery based on the target fusion data and the target model includes: Calculating the change rate of the target fusion voltage and the current fusion voltage to obtain a voltage change rate; Calculating the change rate of the target fusion current and the current fusion current to obtain the current change rate; Calculating the change rate of the target fusion temperature and the current fusion temperature to obtain a temperature change rate; The voltage change rate, the current change rate, and the temperature change rate are input into the target model, and the health state of the battery is output.

4. The battery-based data processing method according to claim 1, characterized in that: When the health status of the battery indicates that the battery is in a fault state, adjusting the charge and discharge strategy of the battery includes: Determine the state of charge of the battery at the current moment to obtain the current state of charge; When the current state of charge is less than a first preset threshold, discharging the battery is prohibited; When the current state of charge is greater than a second preset threshold, charging of the battery is prohibited, wherein the second preset threshold is greater than the first preset threshold.

5. The battery-based data processing method according to claim 1, characterized in that: In the event that the health status of the battery indicates that the battery is in a fault state, the method further includes: Acquire the internal resistance data of the battery and the current data of the battery, wherein the current data of the battery at least includes: the nominal current, and the internal resistance data of the battery at least includes: the battery internal resistance of the battery measured at the current moment; The current magnitudes of the power source and the battery are adjusted based on the internal resistance data of the battery, the current data of the battery and a preset adjustment coefficient.

6. A battery-based data processing device, characterized in that: include: A first acquisition unit is used to acquire operation data of a target power source within a target time period to obtain power source data, wherein the type of the operation data includes at least one of the following: voltage, current, and temperature; A second acquisition unit is used to acquire operation data of a battery within the target time period to obtain battery data, wherein the battery is deployed in the target power source; A fusion unit, used for fusing the power source data and the battery data to obtain target fusion data; A determination unit, configured to determine the health state of the battery based on the target fusion data and the target model, wherein the type of the target model includes: a machine learning model, and the health state of the battery includes one of the following: a normal state and a fault state; A first adjustment unit, configured to adjust a charge and discharge strategy of the battery when the health status of the battery indicates that the battery is in a fault state; The power data includes: the operating data of the target power at n moments, where n is a positive integer; the battery data includes: the operating data of the battery at n moments, where the n moments are within the target time period; the fusion unit includes: a first fusion subunit, which is used to fuse the operating data of the target power at each moment with the operating data of the battery at that moment to obtain the first fused data at each moment, wherein the first fused data at each moment includes at least one of the following: a first fused voltage obtained by fusing the voltage of the target power at that moment with the voltage of the battery at that moment, a current of the target power at that moment and a first fused current obtained by fusing the currents of the battery at that moment, and a first fused temperature obtained by fusing the temperature of the target power source at that moment and the temperature of the battery at that moment; a second fusion subunit, used for fusing the first fused data at n moments to obtain the target fused data, wherein the target fused data includes at least one of the following: a target fused voltage obtained by fusing the first fused voltages at n moments, a target fused current obtained by fusing the first fused currents at n moments, and a target fused temperature obtained by fusing the first fused temperatures at n moments; The second fusion subunit includes: a construction module, which is used to construct an original sequence based on the first fusion data at n moments, wherein the original sequence is used to record the first fusion data at n moments; an accumulation module, which is used to accumulate different numbers of first fusion data in the original sequence respectively to obtain a target sequence; a prediction module, which is used to predict the fusion data at the target moment based on the target sequence to obtain second fusion data, wherein the second fusion data includes: fusion data obtained by fusing the predicted operation data of the target power source at the target moment with the predicted operation data of the battery at the target moment, and the target moment is after the target time period; an acquisition module, which is used to acquire current fusion data, wherein the current fusion data includes: fusion data obtained by fusing the operation data of the target power source at the current moment with the operation data of the battery at the current moment, and the current moment is after the target time period and before the target moment; a fusion module, which is used to perform weighted fusion on the second fusion data and the current fusion data to obtain the target fusion data.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the battery-based data processing method according to any one of claims 1 to 5.

8. An electronic device, characterized in that: It comprises one or more processors and a memory, wherein the memory is used to store one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the battery-based data processing method described in any one of claims 1 to 5.

Images