CN118151009A - Method, device and equipment for determining battery performance degradation reason - Google Patents
Method, device and equipment for determining battery performance degradation reason Download PDFInfo
- Publication number
- CN118151009A CN118151009A CN202410121934.4A CN202410121934A CN118151009A CN 118151009 A CN118151009 A CN 118151009A CN 202410121934 A CN202410121934 A CN 202410121934A CN 118151009 A CN118151009 A CN 118151009A
- Authority
- CN
- China
- Prior art keywords
- battery
- data set
- factor
- index
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000015556 catabolic process Effects 0.000 title claims abstract description 99
- 238000006731 degradation reaction Methods 0.000 title claims abstract description 99
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000004458 analytical method Methods 0.000 claims abstract description 66
- 238000000605 extraction Methods 0.000 claims description 35
- 238000013528 artificial neural network Methods 0.000 claims description 24
- 230000007613 environmental effect Effects 0.000 claims description 23
- 230000015654 memory Effects 0.000 claims description 18
- 230000003287 optical effect Effects 0.000 claims description 14
- 239000000463 material Substances 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 230000006866 deterioration Effects 0.000 claims 2
- 239000007789 gas Substances 0.000 description 11
- 238000005562 fading Methods 0.000 description 9
- 238000010586 diagram Methods 0.000 description 6
- 230000032683 aging Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 238000009826 distribution Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 238000003062 neural network model Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 239000003570 air Substances 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000003247 decreasing effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000000446 fuel Substances 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 239000012080 ambient air Substances 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000004146 energy storage Methods 0.000 description 1
- 230000007787 long-term memory Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/10—Energy storage using batteries
Landscapes
- Secondary Cells (AREA)
Abstract
The application provides a method, a device and equipment for determining a battery performance degradation reason, wherein the method comprises the following steps: acquiring a first data set and a second data set which correspond to each of a plurality of batteries meeting preset requirements; wherein the first data set is used for indicating the value of the influence factor under the full life cycle; the second data set is used for indicating the value of the performance index under the full life cycle; the full life cycle comprises a period when the battery is in an operating state and a period when the battery is in an inactive state; and determining a degradation analysis result of the battery meeting the preset requirements according to each first data set and each second data set. According to the application, the value of the influence factor of the battery under the full life cycle and the value of the battery performance index under the full life cycle are obtained, so that the data of the battery in the working state and the non-working state are integrated, the performance degradation analysis result is more comprehensively analyzed and determined, and the accuracy of the analysis result is ensured.
Description
Technical Field
The present application relates to the field of electronics, and in particular, to a method, an apparatus, and a device for determining a cause of degradation of battery performance.
Background
Currently, batteries are widely used in various fields as an energy storage element. In the related art, when performance degradation analysis is performed on a battery, it is generally determined based on only data of the battery in a charge and discharge operation state.
However, after the battery is produced, the battery is not always in a charge-discharge working state, and the factors influencing the degradation of the battery performance are determined only based on the data analysis in the charge-discharge state, which easily results in inaccurate analysis results.
Disclosure of Invention
The method, the device and the equipment for determining the battery performance degradation cause, the method, the device and the equipment for determining the battery performance degradation cause are used for accurately determining the battery performance degradation cause.
In a first aspect, the present application provides a method for determining a cause of degradation of battery performance, including:
Acquiring a first data set and a second data set which correspond to each of a plurality of batteries meeting preset requirements; wherein the first data set is used for indicating the value of the influence factor under the full life cycle; the second data set is used for indicating the value of the performance index under the full life cycle; the full life cycle comprises a period when the battery is in an operating state and a period when the battery is in an inactive state; the influence factor is an index for influencing the performance degradation of the battery; the performance index is an index for describing the performance of the battery;
Determining a degradation analysis result of the battery meeting the preset requirement according to each first data set and each second data set; the degradation analysis result is used for indicating the influence degree of each influence factor on the degradation of the performance index.
In one possible implementation manner, the first data set includes a first subset corresponding to each of a plurality of influence factors; the first subset comprises the values of the influence factors corresponding to the first subset under the full life cycle;
the second data set comprises a second subset corresponding to each of a plurality of performance indexes; the second subset includes the values of the performance indexes corresponding to the second subset under the full life cycle.
In one possible implementation, the influence factor is any one of an optical factor, a sound factor, an external force factor, an electrical factor, an environmental factor, and a cell rest angle factor; wherein the optical factor is used for indicating an index describing visible light or invisible light; the sound factor is used for indicating an index for describing the environmental noise of the battery; the external force factor is used for indicating an index describing the pressure applied to the outside of the battery; the electrical factor is used for indicating an index describing the current or voltage change of the battery; the environmental factor is used for indicating the gas, temperature, humidity and altitude index of the environment where the battery is located.
In one possible implementation, determining a degradation analysis result of the battery according to each of the first data sets and each of the second data sets includes:
Based on a feature extraction layer of the neural network, carrying out feature extraction processing on the data in the first data set to obtain a feature extraction result; based on each prediction layer in the neural network, determining a prediction result of a performance index corresponding to the prediction layer according to the feature extraction result;
According to the second data set and the prediction results of the performance indexes, the neural network is adjusted to obtain an adjusted network model; and determining a degradation analysis result of the battery according to the adjusted network model.
In one possible implementation, determining the degradation analysis result of the battery according to the adjusted network model includes:
Obtaining a third data set and a fourth data set according to the first data set; the third data set is a result obtained by multiplying the first data set with a first preset value point; the fourth data set is the result of the dot multiplication of the first data set and the second preset value; the first preset value is larger than 1; the second preset value is larger than 0 and smaller than 1;
And determining a degradation analysis result of the battery according to the third data set, the fourth data set and the adjusted network model.
In one possible implementation, the preset requirements are that the internal materials, models and sizes are the same, and the difference between weights of each two batteries in the plurality of batteries is smaller than a preset threshold.
In one possible implementation, the method further includes:
and determining the applicable environment of the battery according to the degradation analysis result of the battery.
In a second aspect, the present application provides a device for determining a cause of degradation of battery performance, including:
The acquisition unit is used for acquiring a first data set and a second data set which correspond to each of a plurality of batteries meeting preset requirements; wherein the first data set is used for indicating the value of the influence factor under the full life cycle; the second data set is used for indicating the value of the performance index under the full life cycle; the full life cycle comprises a period when the battery is in an operating state and a period when the battery is in an inactive state; the influence factor is an index for influencing the performance degradation of the battery; the performance index is an index for describing the performance of the battery;
the first determining unit is used for determining a degradation analysis result of the battery meeting the preset requirement according to each first data set and each second data set; the degradation analysis result is used for indicating the influence degree of each influence factor on the degradation of the performance index.
In one possible implementation manner, the first data set includes a first subset corresponding to each of a plurality of influence factors; the first subset comprises the values of the influence factors corresponding to the first subset under the full life cycle;
the second data set comprises a second subset corresponding to each of a plurality of performance indexes; the second subset includes the values of the performance indexes corresponding to the second subset under the full life cycle.
In one possible implementation, the influence factor is any one of an optical factor, a sound factor, an external force factor, an electrical factor, an environmental factor, and a cell rest angle factor; wherein the optical factor is used for indicating an index describing visible light or invisible light; the sound factor is used for indicating an index for describing the environmental noise of the battery; the external force factor is used for indicating an index describing the pressure applied to the outside of the battery; the electrical factor is used for indicating an index describing the current or voltage change of the battery; the environmental factor is used for indicating the gas, temperature, humidity and altitude index of the environment where the battery is located.
In one possible implementation manner, the first determining unit includes:
The extraction module is used for carrying out feature extraction processing on the data in the first data set based on the feature extraction layer of the neural network to obtain a feature extraction result;
The first determining module is used for determining a prediction result of a performance index corresponding to each prediction layer in the neural network according to the feature extraction result;
The adjusting module is used for adjusting the neural network according to the second data set and the prediction results of the performance indexes to obtain an adjusted network model;
and the second determining module is used for determining a degradation analysis result of the battery according to the adjusted network model.
In one possible implementation manner, the second determining module is specifically configured to:
Obtaining a third data set and a fourth data set according to the first data set; the third data set is a result obtained by multiplying the first data set with a first preset value point; the fourth data set is the result of the dot multiplication of the first data set and the second preset value; the first preset value is larger than 1; the second preset value is larger than 0 and smaller than 1;
And determining a degradation analysis result of the battery according to the third data set, the fourth data set and the adjusted network model.
In one possible implementation, the preset requirements are that the internal materials, models and sizes are the same, and the difference between weights of each two batteries in the plurality of batteries is smaller than a preset threshold.
In one possible implementation, the apparatus further includes:
And the second determining unit is used for determining the applicable environment of the battery according to the degradation analysis result of the battery.
In a third aspect, the present application provides an electronic device comprising: a processor, and a memory communicatively coupled to the processor;
The memory stores computer-executable instructions;
the processor executes computer-executable instructions stored by the memory to implement the method of any one of the first aspects.
In a fourth aspect, the present application provides a computer-readable storage medium having stored therein computer-executable instructions for performing the method of any of the first aspects when executed by a processor.
In a fifth aspect, the application provides a computer program product comprising a computer program which, when executed by a processor, implements the method according to any of the first aspects.
The application provides a method, a device and equipment for determining a battery performance degradation reason, wherein the method comprises the following steps: acquiring a first data set and a second data set which correspond to each of a plurality of batteries meeting preset requirements; wherein the first data set is used for indicating the value of the influence factor under the full life cycle; the second data set is used for indicating the value of the performance index under the full life cycle; the full life cycle comprises a period when the battery is in an operating state and a period when the battery is in an inactive state; and determining a degradation analysis result of the battery meeting the preset requirements according to each first data set and each second data set. According to the application, the value of the influence factor of the battery under the full life cycle and the value of the battery performance index under the full life cycle are obtained, so that the data of the battery in the working state and the non-working state are integrated, the performance degradation analysis result is more comprehensively analyzed and determined, and the accuracy of the analysis result is ensured.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.
Fig. 1 is a flow chart of a method for determining a cause of degradation of battery performance according to an embodiment of the present application;
Fig. 2 is a flowchart of a second method for determining a cause of degradation of battery performance according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of a device for determining a cause of degradation of battery performance according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a second device for determining a cause of degradation of battery performance according to an embodiment of the present application;
Fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Specific embodiments of the present application have been shown by way of the above drawings and will be described in more detail below. The drawings and the written description are not intended to limit the scope of the inventive concepts in any way, but rather to illustrate the inventive concepts to those skilled in the art by reference to the specific embodiments.
Detailed Description
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the application. Rather, they are merely examples of apparatus and methods consistent with aspects of the application.
From the time of leaving the battery, the performance of the battery begins to continuously decline, and the performance of the battery can be performance indexes such as charge capacity, energy efficiency and the like corresponding to the battery. There are many aspects to the performance degradation of batteries, not just a single capacity degradation or an increase in internal resistance, and further determination of whether there is a correlation between different performance degradation is needed. In addition, in the related art, test analysis is performed only for single battery performance, and correlation between battery performance indexes is easily ignored.
In one possible implementation manner, in order to analyze the degradation of the performance of the battery, working condition data corresponding to the battery in an alarm state may be acquired, and a degradation analysis result corresponding to the battery may be determined based on the acquired working condition data. However, the above analysis method discards data of a large amount of batteries in a normal operation state, and does not pay attention to the normal operation state of the batteries.
In one possible implementation, the battery is subjected to an aging cycle test, that is, a repeated charge-discharge cycle test is continuously performed on the battery until the aging state index of the battery reaches below a set threshold. Analyzing the degradation reason of the battery performance through the battery working condition data in the aging cycle test process; however, the aging cycle test method cannot truly simulate the actual use condition of the battery in the use process.
In one possible implementation, the analysis and prediction of the fuel cell performance degradation may be performed based on the data of the fuel cell vehicle during the actual road running, however, the above analysis method predicts the degradation of the battery performance from the aspect of the vehicle running data, which is equivalent to recognizing that the degradation of the battery is only related to the accumulated working time, and cannot fully analyze the cause of the degradation of the battery.
The application provides a method, a device and equipment for determining a battery performance degradation reason, which are used for solving the technical problems.
The following describes the technical scheme of the present application and how the technical scheme of the present application solves the above technical problems in detail with specific embodiments. The following embodiments may be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments. Embodiments of the present application will be described below with reference to the accompanying drawings.
Fig. 1 is a flow chart of a method for determining a cause of degradation of battery performance according to an embodiment of the present application, as shown in fig. 1, the method includes the following steps:
S101, acquiring a first data set and a second data set which correspond to each of a plurality of batteries meeting preset requirements; wherein the first data set is used for indicating the value of the influence factor under the full life cycle; the second data set is used for indicating the value of the performance index under the full life cycle; the full life cycle comprises a period when the battery is in an operating state and a period when the battery is in an inactive state; the influence factor is an index for influencing the performance degradation of the battery; the performance index is an index describing the performance of the battery.
In this embodiment, when analyzing the cause of performance degradation of the battery, first, a first data set and a second data set corresponding to each of a plurality of batteries meeting a preset requirement may be acquired.
The preset requirements may be requirements meeting preset model specifications, so as to ensure that each battery is a same type of battery. For example, the preset model specification may be one or more of a battery model, a battery lot number, a battery specification, a battery size, a battery manufacturer, a battery place of production, a battery line, a battery gear, a battery material system.
Further, the full life cycle in the present embodiment includes a period in which the battery is in an operating state and a period in which the battery is in an inactive state. The working state of the battery comprises the charging state of the battery and the discharging state of the battery. Specifically, the method for determining whether the battery is in the operating state may be determined by determining the magnitude of the operating current of the battery. When the working current of the battery is larger than a preset value, the battery can be determined to be in a working state; and if the working current of the battery is smaller than or equal to a preset value, determining that the battery is in an unoperated state.
In one possible implementation, the full life cycle of the battery may be understood as the period of time from the time the battery is manufactured to the current time.
The influence factor in this embodiment can be understood as an index that affects the battery performance. In this embodiment, the index corresponding to the influence factor is not particularly limited. The first data set corresponding to the battery contains the data of the influence factors of the battery in the whole life cycle. It should be noted that, in the present embodiment, the influence factor may correspond to a plurality of indicators in practical application. That is, the first dataset includes values for a plurality of different influencing factors each at full life cycle.
The performance index in the present embodiment is an index for describing the performance of the battery. Also, the specific type of performance index is not particularly limited herein. And the second data set corresponding to the battery comprises the data of the performance index of the battery in the whole life cycle.
S102, determining a degradation analysis result of the battery meeting preset requirements according to each first data set and each second data set; the fading analysis result is used for indicating the influence degree of each influence factor on the performance index fading.
For example, after the first data set and the second data set corresponding to each battery are obtained, the degradation analysis result corresponding to the battery may be determined by analysis according to each first data set and each second data set, that is, the degree of influence of each influence factor corresponding to the first data set on degradation of the battery performance index in the whole life cycle.
In one possible implementation manner, when determining the degradation analysis result according to each first data set and each second data set, firstly, the influence weight of each influence factor on the performance index degradation in the second data set in each period corresponding to the full life cycle can be determined through a traditional data fitting mode. For example, the first dataset includes 3 sequences of values for each of the influencing factors over the full life cycle. And the second data set includes 1 sequence of values of the performance indicators under the full lifecycle. Through the data fitting mode, the value of the influence degree of each influence factor on the performance index under each period contained in the full life cycle can be determined. Specifically, the data fitting method may be a conventional fitting method such as linear fitting, nonlinear fitting, least squares fitting, etc.
It can be understood that in this embodiment, the performance degradation analysis result is more comprehensively analyzed and determined by acquiring the value of the influence factor under the full life cycle and the value of the battery performance index under the full life cycle so as to synthesize the data under the working state and the non-working state of the battery, thereby ensuring the accuracy of the analysis result.
In a possible implementation manner, on the basis of the foregoing embodiment, the first dataset in this embodiment includes a first subset corresponding to each of the plurality of influence factors; the first subset comprises the values of the influence factors corresponding to the first subset under the full life cycle; the second data set comprises a second subset corresponding to each of the plurality of performance indexes; the second subset includes the values of the performance indicators corresponding to the second subset under the full life cycle.
In this embodiment, the first data set corresponding to the battery includes values of a plurality of influencing factors under the full life cycle. The second data set includes a plurality of performance indicators each taking on values over a full life cycle.
Further, in this embodiment, a plurality of influence factors are combined, and the influence of each influence factor on the degradation of each performance index is analyzed together. For example, a mimo model may be constructed by the first data set and the second data set, and the degradation analysis result corresponding to the battery may be determined by continuously adjusting parameters of the mimo model.
It can be appreciated that in this embodiment, since there may be a correlation between the performance indexes, in this embodiment, the same model may be selected to determine the influence degree of each influence factor on each index at the same time, so as to avoid the problem that the correlation between the performance indexes is ignored due to the manner of performing the regression analysis prediction on the single performance index based on the plurality of influence factors provided in the related art.
In one possible implementation, the influencing factor is any one of an optical factor, a sound factor, an external force factor, an electrical factor, an environmental factor, and a cell rest angle factor; wherein the optical factor is used for indicating an index describing visible light or invisible light; the sound factor is used for indicating an index for describing the environmental noise of the battery; the external force factor is used for indicating an index describing the pressure applied to the outside of the battery; the electrical factor is used to indicate an indicator describing a change in current or voltage of the battery; the environmental factor is used to indicate an indicator of the gas, or humidity, temperature, altitude at which the battery is located.
Illustratively, in this embodiment, the influence factors of the battery are divided into multiple factors such as sound, light, force, electricity, environment, and the like, so as to comprehensively analyze the influence factors corresponding to the battery.
Specifically, the above-mentioned influence factor may be an index in the optical factors. The optical factor may be understood as an index describing visible light and/or invisible light in the operating environment in which the battery is located. Such as ambient light intensity, ambient light spectral distribution, etc. For example, some types of visible light may affect the temperature of the battery, or some types of invisible light may affect the materials inside the battery, etc.
Wherein the external force factor can be understood as an index of the pressure applied to the outside of the battery; for example, the pre-tightening force corresponding to the battery, the change of the pre-tightening force or the change of the battery movement can be used to cause the changed environmental vibration frequency, the accumulated energy of the environmental vibration and the like.
The acoustic factor may be understood as an index corresponding to noise in the environment where the battery is located, for example, may be an index such as an environmental noise intensity.
In addition, there are some indicators classified as environmental factors, such as gas concentration distribution in the environment in which the battery is located, ambient humidity, ambient air pressure, altitude, and the like. For example, in practical applications, some gases in the environment or moisture in the environment may be corrosive to the battery itself, and thus some special gases in the environment and environmental humidity need to be considered.
In addition, the cell placement angle, for example, is an indicator of the placement angle corresponding to the battery when the battery is placed.
Further, the power factor may specifically be an index such as a voltage or a current corresponding to the battery. Further, the present invention may be applied to an indicator such as a battery remaining capacity (SOC) obtained based on a change in current and voltage of the battery, battery power, accumulated Charge amount, accumulated energy, depth of discharge (Depth of discharge, DOD for short), number of current changes, frequency of current changes, number of power changes, and frequency of power changes.
It should be noted that, for the above-mentioned method for obtaining each index, detailed description is not given in this embodiment. In addition, in practical application, the influence factors which need to be selected at this time can be determined according to the actual use situation of the battery. For example, when a battery is operated in some special chemical industry scenarios, the gas in the environment where the battery is located may be different from the ambient gas in daily life, and thus the gas in the environment is introduced as a consideration.
It will be appreciated that in this embodiment, the influence factors corresponding to the battery in various aspects are considered through analysis, so as to comprehensively analyze the main factors of the performance degradation of the battery.
In practical applications, the impact factor corresponding to the first data set may be one or more processed results such as fourier transform, laplace transform, max, min, mean, median, mode, variance, standard deviation, integral, n-th power (n may be any real number or imaginary number or complex number), and m-th bit (m may be any real number between 0 and 100) of each index in the above examples.
Fig. 2 is a flow chart of a second method for determining a cause of degradation of battery performance according to an embodiment of the present application, as shown in fig. 2, the method includes the following steps:
S201, acquiring a first data set and a second data set corresponding to each of a plurality of batteries meeting preset requirements; wherein the first data set is used for indicating the value of the influence factor under the full life cycle; the second data set is used for indicating the value of the performance index under the full life cycle; the full life cycle comprises a period when the battery is in an operating state and a period when the battery is in an inactive state; the influence factor is an index for influencing the performance degradation of the battery; the performance index is an index describing the performance of the battery.
For example, the specific principle of step S201 in this embodiment may refer to step S101, which is not described herein. It should be noted that, the second data set in this embodiment includes a plurality of values of performance indicators under the full life cycle.
In one possible implementation, the preset requirements are that the same internal materials, model numbers, and sizes are the same, and the difference between weights of each two batteries in the plurality of batteries is less than a preset threshold.
In this embodiment, parameters corresponding to the required internal materials, model and size of the batteries can be set in the preset requirements, and it is further defined that the weight difference between every two batteries meeting the above parameter setting must be smaller than a preset threshold.
It can be understood that in the actual production process, although the labels corresponding to the plurality of batteries are marked with the same internal materials, sizes, models and other parameters, certain manufacturing incapability still exists in the battery manufacturing process, for example, the materials in the batteries can have tiny differences, so that further on the basis of the plurality of batteries meeting the same requirements of parameters, the plurality of batteries with the same battery weight can be further screened as the battery parameters for finally analyzing the battery degradation result, so that the difference among the plurality of batteries is reduced as much as possible, and the accuracy of the finally obtained battery degradation analysis result is ensured.
S202, performing feature extraction processing on data in a first data set based on a feature extraction layer of a neural network to obtain a feature extraction result; and determining a prediction result of the performance index corresponding to the prediction layer according to the feature extraction result based on each prediction layer in the neural network.
In this embodiment, after the first data set and the second data set corresponding to the plurality of batteries meeting the same preset requirement are acquired, the first data set may be input to the feature extraction layer of the neural network, and feature extraction processing may be performed on the input data based on the feature extraction layer of the neural network.
Note that, in this embodiment, the structure of the feature extraction layer corresponding to the neural network is not particularly limited, and may include a plurality of convolution layers, for example.
In addition, in this embodiment, a prediction layer corresponding to each performance index corresponding to the data in the second data set is set. Each prediction layer determines the prediction result of the performance index corresponding to the prediction layer by acquiring the feature extraction result extracted by the feature extraction layer.
That is, the values corresponding to the performance indexes are predicted based on the feature extraction results extracted corresponding to the same feature extraction layer, so as to implement a scheme of simultaneously predicting a plurality of performance indexes.
And S203, adjusting the neural network according to the second data set and the prediction result of each performance index to obtain an adjusted network model.
In this embodiment, after the prediction results corresponding to the performance indexes are obtained according to the prediction layer of the neural network, the model parameter adjustment may be further performed on the neural network in combination with the second data set corresponding to the first data set input to the neural network, and the steps S202 to S203 are repeated until the preset condition is reached, and then the adjusted network model is obtained. It should be noted that the training process of the neural network model is similar to that in the related art, and will not be repeated here.
S204, determining a degradation analysis result of the battery according to the adjusted network model; the fading analysis result is used for indicating the influence degree of each influence factor on the performance index fading.
Illustratively, after the adjusted network model is obtained, a degradation analysis result of the battery may be determined according to the adjusted network model.
For example, after determining the adjusted network model, the full life cycle may be segmented to obtain a plurality of time periods, and in each time period, a degree of influence of each influence factor on each performance index is determined. Specifically, when the full life cycle is segmented, time division can be performed uniformly based on time; or the time interval division can be performed based on the value change time of the performance index, for example, the residual life of the battery is (98% -100% ], (96% -98% ], (94% -96% ], and the time of each of the three phases is used for segmenting the full life cycle.
After segmentation, for each period, the corresponding fading analysis result at each period may be determined in combination with the average impact Value (MIV) algorithm mentioned in the related art and the adjusted network model.
For example, in each period, the data corresponding to the period in the first data set is increased by ten percent on its own basis, and the increased data is obtained. The data corresponding to the period in the first data set is reduced by ten percent on the basis of the data set, and the reduced data is obtained. And then, respectively inputting the increased data and the decreased data into the adjusted model, and determining the influence degree of each influence factor on each performance index in the period based on the output result of the corresponding model.
It can be appreciated that in this embodiment, modeling is performed jointly by combining one feature layer and multiple prediction layers in the neural network model, so that the neural network model can learn the relevance between the performance indexes in the continuous learning and training process, so as to ensure the accuracy of the finally obtained degradation analysis result.
In a possible implementation manner, step S204 includes the following steps:
Obtaining a third data set and a fourth data set according to the first data set; the third data set is the result of multiplying the first data set by a first preset value; the fourth data set is the result of the first data set multiplied by the second preset value; the first preset value is greater than 1; the second preset value is more than 0 and less than 1; and determining a degradation analysis result of the battery according to the third data set, the fourth data set and the adjusted network model.
In this embodiment, after the adjusted model is acquired, the data in the first data set is directly subjected to the increasing process and the decreasing process without performing time division on the full life cycle, so as to obtain the third data set and the fourth data set.
That is, the above-mentioned method increases the value in the first data set by dot multiplying the first preset value. And the value in the first data set is reduced by multiplying the second preset value point. And then, respectively inputting the third data set and the fourth data set into the adjusted network model to obtain output results corresponding to the third data set and the fourth data set. And determining the average influence change value of each influence factor on each performance index according to the output result, and determining the influence degree of each influence factor on each performance index according to the ordering of the average influence change value of each influence factor on the performance index aiming at each performance index.
It can be understood that in this embodiment, the influence degree of each influence factor on each performance index in the whole life cycle is determined by combining the neural network model and the average influence value algorithm, so as to determine the main factors influencing the performance degradation of the battery.
S205, determining the applicable environment of the battery according to the degradation analysis result of the battery.
In this embodiment, after determining the degradation analysis result corresponding to the battery, the applicable environment corresponding to the battery may be determined by combining the degradation analysis result analysis.
For example, when the degradation analysis result corresponding to the same type of battery at low air pressure has a major role in performance degradation, and the degradation analysis result corresponding to the same type of battery at standard air pressure has a smaller degree of influence on performance degradation, it may be determined that the battery is not suitable for the low air pressure environment.
Or the environment suitable for the battery can be determined by combining the fading analysis results corresponding to the influence factors such as ambient gas, noise and the like in the fading analysis results so as to facilitate the battery screening of the user.
For example, for a type a battery, charge capacity and energy efficiency are used as key battery performance indexes, and the influence of the accumulated charge amount, accumulated discharge amount, SOC of the battery under a zero current condition and the temperature of the battery under the zero current condition on the performance is focused and a model is built. Specifically, in the first step, the change data of the charge capacity and the energy efficiency of a large number of a-type batteries with time is first acquired. The manner of obtaining the charge capacity and the energy efficiency of the battery is not particularly limited herein. And secondly, counting the accumulated charge quantity, accumulated discharge quantity and battery SOC frequency distribution under a zero-current working condition of each A type battery, and changing data of battery temperature frequency distribution with time under the zero-current working condition. And thirdly, taking the data obtained in the second step as input, taking the data obtained in the first step as output, training a long-term and short-term memory network, and adjusting the model structure and model parameters to optimize the overall accuracy of the model so as to complete the establishment of a battery performance degradation model.
Fig. 3 is a schematic structural diagram of a device for determining a cause of degradation of battery performance according to an embodiment of the present application, where, as shown in fig. 3, the device includes:
An acquiring unit 301, configured to acquire a first data set and a second data set corresponding to each of a plurality of batteries meeting a preset requirement; wherein the first data set is used for indicating the value of the influence factor under the full life cycle; the second data set is used for indicating the value of the performance index under the full life cycle; the full life cycle comprises a period when the battery is in an operating state and a period when the battery is in an inactive state; the influence factor is an index for influencing the performance degradation of the battery; the performance index is an index describing the performance of the battery;
A first determining unit 302, configured to determine a degradation analysis result of the battery according to the first data sets and the second data sets; the fading analysis result is used for indicating the influence degree of each influence factor on the performance index fading.
The device provided in this embodiment is configured to implement the technical scheme provided by the method, and the implementation principle and the technical effect are similar and are not repeated.
Fig. 4 is a schematic structural diagram of a second device for determining a cause of degradation of battery performance according to an embodiment of the present application, as shown in fig. 4, on the basis of the embodiment shown in fig. 3, a first data set in this embodiment includes a first subset corresponding to each of a plurality of influencing factors; the first subset comprises the values of the influence factors corresponding to the first subset under the full life cycle; the second data set comprises a second subset corresponding to each of the plurality of performance indexes; the second subset includes the values of the performance indicators corresponding to the second subset under the full life cycle.
In one possible implementation, the influencing factor is any one of an optical factor, a sound factor, an external force factor, an electrical factor, an environmental factor, and a cell rest angle factor; wherein the optical factor is used for indicating an index describing visible light or invisible light; the sound factor is used for indicating an index for describing the environmental noise of the battery; the external force factor is used for indicating an index describing the pressure applied to the outside of the battery; the electrical factor is used to indicate an indicator describing a change in current or voltage of the battery; the environmental factor is used to indicate an indicator of the gas, or temperature, humidity, altitude at which the battery is located.
The first determining unit 302 in the present embodiment includes:
The extraction module 3021 is configured to perform feature extraction processing on the data in the first data set based on the feature extraction layer of the neural network, so as to obtain a feature extraction result;
A first determining module 3022, configured to determine, based on each prediction layer in the neural network, a prediction result of the performance index corresponding to the prediction layer according to the feature extraction result;
an adjustment module 3023, configured to adjust the neural network according to the second data set and the prediction results of the performance indexes, to obtain an adjusted network model;
a second determining module 3024, configured to determine a degradation analysis result of the battery according to the adjusted network model.
In one possible implementation, the second determining module 3024 is specifically configured to:
Obtaining a third data set and a fourth data set according to the first data set; the third data set is the result of multiplying the first data set by a first preset value; the fourth data set is the result of the first data set multiplied by the second preset value; the first preset value is greater than 1; the second preset value is more than 0 and less than 1;
and determining a degradation analysis result of the battery according to the third data set, the fourth data set and the adjusted network model.
In one possible implementation, the preset requirements are that the same internal materials, model numbers, and sizes are the same, and the difference between weights of each two batteries in the plurality of batteries is less than a preset threshold.
In one possible implementation, the apparatus further includes:
and a second determining unit 303, configured to determine an applicable environment of the battery according to a degradation analysis result of the battery.
The device provided in this embodiment is configured to implement the technical scheme provided by the method, and the implementation principle and the technical effect are similar and are not repeated.
In a third aspect, the present application provides an electronic device comprising: a processor, a memory communicatively coupled to the processor;
the memory stores computer-executable instructions;
the processor executes computer-executable instructions stored in the memory to implement the method as in any of the first aspects.
Fig. 5 is a schematic structural diagram of an electronic device according to an embodiment of the present application, as shown in fig. 5, where the electronic device includes:
A processor 291, the electronic device further comprising a memory 292; a communication interface (Communication Interface) 293 and bus 294 may also be included. The processor 291, the memory 292, and the communication interface 293 may communicate with each other via the bus 294. Communication interface 293 may be used for information transfer. The processor 291 may call logic instructions in the memory 294 to perform the methods of the above embodiments.
Further, the logic instructions in memory 292 described above may be implemented in the form of software functional units and stored in a computer-readable storage medium when sold or used as a stand-alone product.
The memory 292 is a computer readable storage medium, and may be used to store a software program, a computer executable program, and program instructions/modules corresponding to the methods in the embodiments of the present application. The processor 291 executes functional applications and data processing by running software programs, instructions and modules stored in the memory 292, i.e., implements the methods of the method embodiments described above.
Memory 292 may include a storage program area that may store an operating system, at least one application program required for functionality, and a storage data area; the storage data area may store data created according to the use of the terminal device, etc. Further, memory 292 may include high-speed random access memory, and may also include non-volatile memory.
The present application provides a computer-readable storage medium having stored therein computer-executable instructions that, when executed by a processor, perform a method of any one of the above.
The present application provides a computer program product comprising a computer program which, when executed by a processor, implements the method of any one of the claims.
Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
It is to be understood that the application is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the application is limited only by the appended claims.
Claims (17)
1. A method for determining a cause of deterioration in battery performance, comprising:
Acquiring a first data set and a second data set which correspond to each of a plurality of batteries meeting preset requirements; wherein the first data set is used for indicating the value of the influence factor under the full life cycle; the second data set is used for indicating the value of the performance index under the full life cycle; the full life cycle comprises a period when the battery is in an operating state and a period when the battery is in an inactive state; the influence factor is an index for influencing the performance degradation of the battery; the performance index is an index for describing the performance of the battery;
Determining a degradation analysis result of the battery meeting the preset requirement according to each first data set and each second data set; the degradation analysis result is used for indicating the influence degree of each influence factor on the degradation of the performance index.
2. The method of claim 1, wherein the first dataset comprises a first subset of the plurality of impact factors, each of the first subset corresponding to a respective one of the plurality of impact factors; the first subset comprises the values of the influence factors corresponding to the first subset under the full life cycle;
the second data set comprises a second subset corresponding to each of a plurality of performance indexes; the second subset includes the values of the performance indexes corresponding to the second subset under the full life cycle.
3. The method of claim 2, wherein the influencing factor is any one of an optical factor, a sound factor, an external force factor, an electrical factor, an environmental factor, a cell rest angle factor; wherein the optical factor is used for indicating an index describing visible light or invisible light; the sound factor is used for indicating an index for describing the environmental noise of the battery; the external force factor is used for indicating an index describing the pressure applied to the outside of the battery; the electrical factor is used for indicating an index describing the current or voltage change of the battery; the environmental factor is used for indicating the gas, temperature, humidity and altitude index of the environment where the battery is located.
4. The method of claim 2, wherein determining a degradation analysis result of the battery from each of the first data sets and each of the second data sets comprises:
Based on a feature extraction layer of the neural network, carrying out feature extraction processing on the data in the first data set to obtain a feature extraction result; based on each prediction layer in the neural network, determining a prediction result of a performance index corresponding to the prediction layer according to the feature extraction result;
According to the second data set and the prediction results of the performance indexes, the neural network is adjusted to obtain an adjusted network model; and determining a degradation analysis result of the battery according to the adjusted network model.
5. The method of claim 4, wherein determining the degradation analysis result of the battery based on the adjusted network model comprises:
Obtaining a third data set and a fourth data set according to the first data set; the third data set is a result obtained by multiplying the first data set with a first preset value point; the fourth data set is the result of the dot multiplication of the first data set and the second preset value; the first preset value is larger than 1; the second preset value is larger than 0 and smaller than 1;
And determining a degradation analysis result of the battery according to the third data set, the fourth data set and the adjusted network model.
6. The method of any one of claims 1-5, wherein the predetermined requirements are the same internal material, model, size, and the difference in weight for each two of the plurality of cells is less than a predetermined threshold.
7. The method according to any one of claims 1-5, further comprising:
and determining the applicable environment of the battery according to the degradation analysis result of the battery.
8. A device for determining a cause of deterioration in battery performance, comprising:
The acquisition unit is used for acquiring a first data set and a second data set which correspond to each of a plurality of batteries meeting preset requirements; wherein the first data set is used for indicating the value of the influence factor under the full life cycle; the second data set is used for indicating the value of the performance index under the full life cycle; the full life cycle comprises a period when the battery is in an operating state and a period when the battery is in an inactive state; the influence factor is an index for influencing the performance degradation of the battery; the performance index is an index for describing the performance of the battery;
the first determining unit is used for determining a degradation analysis result of the battery meeting the preset requirement according to each first data set and each second data set; the degradation analysis result is used for indicating the influence degree of each influence factor on the degradation of the performance index.
9. The apparatus of claim 8, wherein the first dataset comprises a first subset of the plurality of impact factors, respectively; the first subset comprises the values of the influence factors corresponding to the first subset under the full life cycle;
the second data set comprises a second subset corresponding to each of a plurality of performance indexes; the second subset includes the values of the performance indexes corresponding to the second subset under the full life cycle.
10. The apparatus of claim 9, wherein the impact factor is any one of an optical factor, a sound factor, an external force factor, an electrical factor, an environmental factor, a cell rest angle factor; wherein the optical factor is used for indicating an index describing visible light or invisible light; the sound factor is used for indicating an index for describing the environmental noise of the battery; the external force factor is used for indicating an index describing the pressure applied to the outside of the battery; the electrical factor is used for indicating an index describing the current or voltage change of the battery; the environmental factor is used for indicating the gas, temperature, humidity and altitude index of the environment where the battery is located.
11. The apparatus according to claim 10, wherein the first determining unit comprises:
The extraction module is used for carrying out feature extraction processing on the data in the first data set based on the feature extraction layer of the neural network to obtain a feature extraction result;
The first determining module is used for determining a prediction result of a performance index corresponding to each prediction layer in the neural network according to the feature extraction result;
The adjusting module is used for adjusting the neural network according to the second data set and the prediction results of the performance indexes to obtain an adjusted network model;
and the second determining module is used for determining a degradation analysis result of the battery according to the adjusted network model.
12. The apparatus of claim 11, wherein the second determining module is specifically configured to:
Obtaining a third data set and a fourth data set according to the first data set; the third data set is a result obtained by multiplying the first data set with a first preset value point; the fourth data set is the result of the dot multiplication of the first data set and the second preset value; the first preset value is larger than 1; the second preset value is larger than 0 and smaller than 1;
And determining a degradation analysis result of the battery according to the third data set, the fourth data set and the adjusted network model.
13. The device of any one of claims 8-12, wherein the predetermined requirements are the same internal material, model, size, and the difference in weight for each two of the plurality of batteries is less than a predetermined threshold.
14. The apparatus according to any one of claims 8-12, wherein the apparatus further comprises:
And the second determining unit is used for determining the applicable environment of the battery according to the degradation analysis result of the battery.
15. An electronic device, comprising: a processor, and a memory communicatively coupled to the processor;
The memory stores computer-executable instructions;
The processor executes computer-executable instructions stored in the memory to implement the method of any one of claims 1-7.
16. A computer readable storage medium having stored therein computer executable instructions which when executed by a processor are adapted to carry out the method of any one of claims 1-7.
17. A computer program product comprising a computer program which, when executed by a processor, implements the method of any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410121934.4A CN118151009A (en) | 2024-01-29 | 2024-01-29 | Method, device and equipment for determining battery performance degradation reason |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410121934.4A CN118151009A (en) | 2024-01-29 | 2024-01-29 | Method, device and equipment for determining battery performance degradation reason |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118151009A true CN118151009A (en) | 2024-06-07 |
Family
ID=91293804
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410121934.4A Pending CN118151009A (en) | 2024-01-29 | 2024-01-29 | Method, device and equipment for determining battery performance degradation reason |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118151009A (en) |
-
2024
- 2024-01-29 CN CN202410121934.4A patent/CN118151009A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108896914B (en) | Gradient lifting tree modeling and prediction method for health condition of lithium battery | |
| CN108139446B (en) | Battery test system for predicting battery test result | |
| Zhou et al. | A fast screening framework for second-life batteries based on an improved bisecting K-means algorithm combined with fast pulse test | |
| Cui et al. | A dynamic spatial-temporal attention-based GRU model with healthy features for state-of-health estimation of lithium-ion batteries | |
| CN112666480B (en) | Battery life prediction method based on characteristic attention of charging process | |
| CN109613440B (en) | Battery grading method, device, equipment and storage medium | |
| CN112834945A (en) | Evaluation model establishing method, battery health state evaluation method and related product | |
| CN112180258B (en) | Method, device, medium, terminal and system for measuring average coulombic efficiency of battery | |
| CN114651183A (en) | Battery performance prediction | |
| CN114047452B (en) | Method and device for determining cycle life of battery | |
| CN111812515A (en) | XGboost model-based lithium ion battery state of charge estimation | |
| CN109633448B (en) | Method and device for identifying battery health state and terminal equipment | |
| CN114818831B (en) | Bidirectional lithium ion battery fault detection method and system based on multi-source perception | |
| CN109800446B (en) | Method and device for estimating voltage inconsistency in discharging process of lithium ion battery | |
| CN112666479B (en) | Battery life prediction method based on charge cycle fusion | |
| CN109768340B (en) | Method and device for estimating voltage inconsistency in battery discharge process | |
| CN114280479A (en) | Electrochemical impedance spectrum-based rapid sorting method for retired batteries | |
| CN115270454A (en) | Battery life prediction method and related equipment | |
| CN117148177A (en) | Method and device for evaluating dynamic consistency of battery and computer equipment | |
| CN115389954A (en) | Battery capacity estimation method, electronic equipment and readable storage medium | |
| CN115754726A (en) | Battery life prediction and maintenance method, electronic equipment and storage medium | |
| CN114578234A (en) | Lithium ion battery degradation and capacity prediction model considering causality characteristics | |
| CN112084459A (en) | Method and device for predicting battery charge-discharge cycle life, electronic terminal and storage medium | |
| CN117175664B (en) | Energy storage charging equipment output power self-adaptive adjusting system based on use scene | |
| Lamprecht et al. | Random forest regression of charge balancing data: A state of health estimation method for electric vehicle batteries |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination |