CN115267558A - Service life prediction and state estimation method of bidirectional lithium ion battery - Google Patents
Service life prediction and state estimation method of bidirectional lithium ion battery Download PDFInfo
- Publication number
- CN115267558A CN115267558A CN202211205391.1A CN202211205391A CN115267558A CN 115267558 A CN115267558 A CN 115267558A CN 202211205391 A CN202211205391 A CN 202211205391A CN 115267558 A CN115267558 A CN 115267558A
- Authority
- CN
- China
- Prior art keywords
- target
- lithium ion
- ion battery
- bidirectional
- data
- 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
- HBBGRARXTFLTSG-UHFFFAOYSA-N Lithium ion Chemical compound [Li+] HBBGRARXTFLTSG-UHFFFAOYSA-N 0.000 title claims abstract description 105
- 229910001416 lithium ion Inorganic materials 0.000 title claims abstract description 105
- 230000002457 bidirectional effect Effects 0.000 title claims abstract description 91
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000003062 neural network model Methods 0.000 claims abstract description 32
- 238000013135 deep learning Methods 0.000 claims abstract description 17
- 238000010586 diagram Methods 0.000 claims description 39
- 238000000605 extraction Methods 0.000 claims description 19
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000003247 decreasing effect Effects 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 abstract description 7
- 238000013136 deep learning model Methods 0.000 abstract description 5
- 238000012549 training Methods 0.000 description 8
- 238000010801 machine learning Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 238000004590 computer program Methods 0.000 description 4
- 230000007423 decrease Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000003190 augmentative effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000003042 antagnostic effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/367—Software therefor, e.g. for battery testing using modelling or look-up tables
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]
- G01R31/392—Determining battery ageing or deterioration, e.g. state of health
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M10/00—Secondary cells; Manufacture thereof
- H01M10/42—Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells
- H01M10/4285—Testing apparatus
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Chemical & Material Sciences (AREA)
- Chemical Kinetics & Catalysis (AREA)
- General Chemical & Material Sciences (AREA)
- Electrochemistry (AREA)
- Manufacturing & Machinery (AREA)
- Charge And Discharge Circuits For Batteries Or The Like (AREA)
Abstract
The invention discloses a service life prediction and state estimation method of a bidirectional lithium ion battery, which comprises the steps of acquiring battery characteristic data corresponding to a target bidirectional lithium ion battery at each moment in a continuous time period; determining time sequence data corresponding to the target bidirectional lithium ion battery according to the battery characteristic data respectively corresponding to each moment; inputting the time series data into a target neural network model to obtain a first prediction state corresponding to a target bidirectional lithium ion battery; inputting the battery characteristic data corresponding to each moment into a target deep learning prediction model to obtain a second prediction state corresponding to the target bidirectional lithium ion battery; and determining the corresponding predicted service life of the target bidirectional lithium ion battery according to the first predicted state and the second predicted state. The invention predicts the battery life of the bidirectional lithium ion battery through the neural network model and the deep learning model, and solves the problems of high labor cost and inaccurate judgment result in the prior art for determining the battery life according to artificial experience analysis.
Description
Technical Field
The invention relates to the field of data processing, in particular to a service life prediction and state estimation method for a bidirectional lithium ion battery.
Background
The traditional battery life prediction is mainly based on manual experience analysis, a large number of relevant professionals are needed to measure the voltage, the current, the pressure difference, the temperature and the like of a battery on site, the remaining life of the battery is judged according to experience, certain dangerous factors exist, a large number of labor costs need to be consumed, and more importantly, due to the existence of subjectivity, the judgment result is prone to being inaccurate.
Thus, there is a need for improvement and development of the prior art.
Disclosure of Invention
The invention aims to solve the technical problems that in the prior art, a method for predicting the service life and estimating the state of a bidirectional lithium ion battery is provided, and the problems that in the prior art, the service life of the battery is determined according to manual experience analysis, a large amount of labor cost is consumed, and the judgment result is inaccurate due to subjectivity are solved.
The technical scheme adopted by the invention for solving the problems is as follows:
in a first aspect, an embodiment of the present invention provides a method for predicting a lifetime and estimating a state of a bidirectional lithium ion battery, where the method includes:
acquiring battery characteristic data respectively corresponding to a target bidirectional lithium ion battery at a plurality of moments in a continuous time period;
determining time sequence data corresponding to the target bidirectional lithium ion battery according to the battery characteristic data respectively corresponding to the plurality of moments;
inputting the time sequence data into a target neural network model to obtain a first prediction state corresponding to the target bidirectional lithium ion battery;
inputting the battery characteristic data corresponding to the moments into a target deep learning prediction model to obtain a second prediction state corresponding to the target bidirectional lithium ion battery;
and determining the corresponding predicted service life of the target bidirectional lithium ion battery according to the first predicted state and the second predicted state.
In one embodiment, the time series data is a time series plot having time on the abscissa and amplitude on the ordinate; the time series diagram comprises a plurality of data points, the data points correspond to the moments one by one, the abscissa corresponding to each data point is determined based on the moment corresponding to the data point, and the ordinate corresponding to each data point is determined based on the battery characteristic data at the moment corresponding to the data point.
In one embodiment, the inputting the time-series data into the target neural network model to obtain a first predicted state corresponding to the target bi-directional lithium ion battery includes:
inputting the time series diagram into the feature extraction module to obtain a polar coordinate diagram corresponding to the time series diagram, wherein the polar coordinate diagram comprises a plurality of polar coordinate points, and the polar coordinate points correspond to the data points one by one;
and inputting the polar coordinate graph into the classification module to obtain the first prediction state.
In one embodiment, the inputting the time-series diagram into the feature extraction module to obtain a polar coordinate diagram corresponding to the time-series diagram includes:
inputting the time series diagram into the feature extraction module, and determining polar coordinate point sets corresponding to the data points respectively through the feature extraction module, wherein each polar coordinate point set comprises a plurality of polar coordinate points, and each polar coordinate point in the same polar coordinate point set is in a rotational symmetry relationship;
and determining the polar coordinate graph according to the polar coordinate point sets respectively corresponding to the data points.
In one embodiment, the method for determining the polar coordinate point set corresponding to each data point includes:
obtaining the maximum amplitude value and the minimum amplitude value corresponding to the time series diagram;
acquiring a preset target value, and determining an associated data point corresponding to each data point according to the target value;
acquiring a plurality of preset angles, wherein the angles are sequentially increased or decreased by preset angle values;
and determining the phases of a plurality of polar coordinate points corresponding to the data point according to the plurality of angles, the amplitude corresponding to the associated data point, the maximum amplitude value and the minimum amplitude value, wherein the phases corresponding to the plurality of polar coordinate points respectively correspond to the plurality of angles in a one-to-one manner.
In one embodiment, the determining the phase of the polar coordinate points corresponding to the data point according to the angles, the amplitude corresponding to the associated data point, the maximum amplitude value, and the minimum amplitude value includes:
inputting the amplitudes, the maximum amplitude and the minimum amplitude corresponding to the angles and the associated data points in sequence into a target calculation formula to obtain the phases corresponding to the polar coordinate points in the polar coordinate point set corresponding to the data points respectively;
the target calculation formula is as follows:
wherein the content of the first and second substances,
in order to be the amplitude value,
in order to be the phase position,
for the maximum value of the amplitude value,
is the amplitude minimum, t is the target value,
g is one of a plurality of angles and is a preset fixed value.
In one embodiment, the determining the predicted life corresponding to the target bidirectional lithium ion battery according to the first predicted state and the second predicted state includes:
determining a first residual charge and discharge frequency corresponding to the target bidirectional lithium ion battery according to the first prediction state;
determining a second residual charge and discharge frequency corresponding to the target bidirectional lithium ion battery according to the second prediction state;
and determining the target residual charge and discharge frequency according to the first residual charge and discharge frequency and the second residual charge and discharge frequency.
In a second aspect, an embodiment of the present invention further provides a device for predicting a lifetime and estimating a state of a bidirectional lithium ion battery, where the device includes:
the data acquisition module is used for acquiring battery characteristic data respectively corresponding to a target bidirectional lithium ion battery at a plurality of moments in a continuous time period;
according to the battery characteristic data respectively corresponding to a plurality of moments, determining time sequence data corresponding to the target bidirectional lithium ion battery;
the first prediction module is used for inputting the time sequence data into a target neural network model to obtain a first prediction state corresponding to the target bidirectional lithium ion battery;
the second prediction module is used for inputting the battery characteristic data corresponding to the moments into a target deep learning prediction model to obtain a second prediction state corresponding to the target bidirectional lithium ion battery;
and the service life predicting module is used for determining the predicted service life corresponding to the target bidirectional lithium ion battery according to the first predicted state and the second predicted state.
In a third aspect, an embodiment of the present invention further provides a terminal, where the terminal includes a memory and one or more processors; the memory stores one or more programs; the program comprises instructions for executing the method for predicting the service life and estimating the state of the bidirectional lithium ion battery; the processor is configured to execute the program.
In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, on which a plurality of instructions are stored, where the instructions are adapted to be loaded and executed by a processor to implement the steps of the method for predicting lifetime and estimating state of a bidirectional lithium ion battery described above.
The invention has the beneficial effects that: according to the embodiment of the invention, battery characteristic data respectively corresponding to each moment of a target bidirectional lithium ion battery in a continuous time period is obtained; determining time sequence data corresponding to the target bidirectional lithium ion battery according to the battery characteristic data respectively corresponding to each moment; inputting the time sequence data into a target neural network model to obtain a first prediction state corresponding to a target bidirectional lithium ion battery; inputting the battery characteristic data corresponding to each moment into a target deep learning prediction model to obtain a second prediction state corresponding to the target bidirectional lithium ion battery; and determining the corresponding predicted service life of the target bidirectional lithium ion battery according to the first predicted state and the second predicted state. The invention predicts the battery life of the bidirectional lithium ion battery through the neural network model and the deep learning model, and solves the problems of high labor cost and inaccurate judgment result in the prior art for determining the battery life according to artificial experience analysis.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the description of the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments described in the present invention, and it is also possible for those skilled in the art to obtain other drawings based on the drawings without creative efforts.
Fig. 1 is a schematic flowchart of a method for predicting a lifetime and estimating a state of a bi-directional lithium ion battery according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of a time sequence chart provided by the embodiment of the invention.
Fig. 3 is a schematic diagram of a polar diagram provided by an embodiment of the invention.
Fig. 4 is a schematic diagram of internal modules of a lifetime prediction and state estimation apparatus for a bidirectional lithium ion battery according to an embodiment of the present invention.
Fig. 5 is a schematic block diagram of a terminal according to an embodiment of the present invention.
Detailed Description
The invention discloses a method for predicting the service life and estimating the state of a bidirectional lithium ion battery, which is further described in detail below by referring to the attached drawings and embodiments in order to make the purpose, the technical scheme and the effect of the invention clearer and clearer. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As used herein, the singular forms "a", "an", "the" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. It will be understood that when an element is referred to as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Further, "connected" or "coupled" as used herein may include wirelessly connected or wirelessly coupled. As used herein, the term "and/or" includes all or any element and all combinations of one or more of the associated listed items.
It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the prior art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein.
The traditional battery life prediction is mainly based on manual experience analysis, a large number of relevant professionals are needed to measure the voltage, the current, the pressure difference, the temperature and the like of a battery on site, the remaining life of the battery is judged according to experience, certain dangerous factors exist, a large amount of labor cost needs to be consumed, and more importantly, due to the existence of subjectivity, the judgment result is prone to being inaccurate.
In order to overcome the defects in the prior art, the invention provides a method for predicting the service life and estimating the state of a bidirectional lithium ion battery, which comprises the steps of acquiring battery characteristic data respectively corresponding to a target bidirectional lithium ion battery at a plurality of moments in a continuous time period; determining time sequence data corresponding to the target bidirectional lithium ion battery according to the battery characteristic data respectively corresponding to the plurality of moments; inputting the time sequence data into a target neural network model to obtain a first prediction state corresponding to the target bidirectional lithium ion battery; inputting the battery characteristic data corresponding to the moments into a target deep learning prediction model to obtain a second prediction state corresponding to the target bidirectional lithium ion battery; and determining the corresponding predicted service life of the target bidirectional lithium ion battery according to the first predicted state and the second predicted state. The invention predicts the battery life of the bidirectional lithium ion battery by combining the neural network model and the deep learning model, and solves the problems that the battery life is determined according to manual experience analysis in the prior art, a large amount of labor cost is required to be consumed, and the judgment result is inaccurate due to subjectivity.
As shown in fig. 1, the method comprises the steps of:
step S100, battery characteristic data corresponding to the target bidirectional lithium ion battery at a plurality of moments in a continuous time period are obtained.
Specifically, the target bidirectional lithium ion battery in this embodiment may be any battery that currently needs to be subjected to battery life prediction. Since the battery characteristic data may reflect the current battery state of the target bi-directional lithium ion battery, such as temperature, voltage, current, and the like, the present embodiment needs to obtain the battery characteristic data of the target bi-directional lithium ion battery at several times within a continuous time period, and determine the battery life of the target bi-directional lithium ion battery by analyzing the change of the battery characteristic data at these times.
As shown in fig. 1, the method further comprises the steps of:
and S200, determining time sequence data corresponding to the target bidirectional lithium ion battery according to the battery characteristic data respectively corresponding to the plurality of moments.
Specifically, in this embodiment, a neural network model needs to be subsequently used for predicting the battery life, and the neural network model has a fixed input format, so that the time series data is obtained by converting the acquired battery characteristic data at each time into a time series format that can be processed by the neural network model.
In one implementation, the time series data is a time series plot with time on the abscissa and amplitude on the ordinate; the time series diagram comprises a plurality of data points, the data points correspond to the moments one by one, the abscissa corresponding to each data point is determined based on the moment corresponding to the data point, and the ordinate corresponding to each data point is determined based on the battery characteristic data at the moment corresponding to the data point.
Specifically, as shown in fig. 2, the time-series data in the present embodiment is in the form of a time-series chart. A plurality of data points in the time series plot, each data point representing battery characteristic data for a time instant. For each data point, its abscissa is determined based on the corresponding time instant and its ordinate is determined based on the corresponding battery characteristic data. And analyzing the position distribution of each data point in the time series diagram to obtain the current state of the target bidirectional lithium ion battery.
As shown in fig. 1, the method further comprises the steps of:
and S300, inputting the time sequence data into a target neural network model to obtain a first prediction state corresponding to the target bidirectional lithium ion battery.
Specifically, in this embodiment, a target neural network model is trained in advance, and since the target neural network model is trained in advance through a large amount of training data, data features of time series data of different battery states have been learned, so that the currently obtained time series data is input into the target neural network model, and the target neural network model can classify the target bidirectional lithium ion battery based on the input time series data, thereby outputting a first prediction state currently corresponding to the target bidirectional lithium ion battery.
In one implementation, the target neural network model includes a feature extraction module and a classification module, and the step S300 specifically includes the following steps:
step S301, inputting the time series graph into the feature extraction module to obtain a polar coordinate graph corresponding to the time series graph, wherein the polar coordinate graph comprises a plurality of polar coordinate points, and the plurality of polar coordinate points correspond to the plurality of data points one by one;
step S302, inputting the polar coordinate graph into the classification module to obtain the first prediction state.
Specifically, the target neural network model in this embodiment mainly includes two parts, one is a feature extraction module, and the other is a classification module. After the time-series graph is input into the feature extraction module for the feature extraction module, the feature extraction module determines a corresponding polar coordinate point for each data point and outputs a polar coordinate graph containing the polar coordinate points corresponding to the data points respectively. And inputting the polar coordinate graph into a classification module aiming at the classification module, wherein the classification module classifies the current state of the target bidirectional lithium ion battery aiming at the position distribution of each polar coordinate in the input polar coordinate graph, and then outputs a first prediction state corresponding to the target bidirectional lithium ion battery. As shown in fig. 2, since the positions of the data points are closely distributed in the time-series chart, it is difficult to extract a slight change in the position distribution of the data points from the original time-series chart. As shown in fig. 2 and 3, in the embodiment, the time-series diagram is first converted into a polar coordinate diagram, so that the small change of the position distribution of each data point can be amplified, and the classification module is further prompted to obtain a more accurate classification result.
In one implementation, step S301 specifically includes the following steps:
step S3011, inputting the time-series graph into the feature extraction module, and determining, by the feature extraction module, polar coordinate point sets corresponding to the plurality of data points, where each polar coordinate point set includes a plurality of polar coordinate points, and each polar coordinate point in the same polar coordinate point set is in a rotational symmetry relationship.
Specifically, in this embodiment, each data point corresponds to an equal number of polar coordinate points in the polar coordinate graph. For each data point, the feature extraction module firstly determines a basic point in the polar coordinate graph according to the time corresponding to the data point and the battery data feature, then rotates the basic point for a preset number of times to obtain a plurality of branch points corresponding to the basic point, and forms a polar coordinate point set corresponding to the data point based on the basic point and the plurality of branch points. Therefore, for each data point, there are multiple corresponding polar coordinate points, and each polar coordinate point is in a rotational symmetry relationship. For example, as shown in fig. 3, the polar plot exhibits a rotationally symmetric petal shape. In the embodiment, the number of the polar coordinate points in the polar coordinate graph is increased by generating the plurality of polar coordinate points corresponding to each data point, so that the tiny change of the position distribution of each data point is amplified, and a classification module is prompted to obtain a more accurate classification result.
In one implementation, the method for determining the set of polar coordinate points corresponding to each of the data points includes:
step S30111, obtaining a maximum amplitude value and a minimum amplitude value corresponding to the time series diagram;
step S30112, obtaining a preset target value, and determining an associated data point corresponding to each data point according to the target value;
step S30113, obtaining a plurality of preset angles, wherein the angles are sequentially increased or decreased by a preset angle value;
step S30114, determining phases of the plurality of polar coordinate points corresponding to the data point according to the plurality of angles, the amplitudes corresponding to the associated data points, the maximum amplitude value, and the minimum amplitude value, where the phases corresponding to the plurality of polar coordinate points respectively correspond to the plurality of angles one to one.
In short, each data point needs to determine its corresponding polar coordinate point set based on its corresponding associated data point, where the associated data point of each data point is separated from the data point by the ordinal number of the target value. For example, the target value is t, the data point
The corresponding associated data point is
. Specifically, firstly, it is necessary to obtain the amplitude extremum and associated data point of the time series diagram
The amplitude value in the time sequence chart and a plurality of preset angle values are based on the amplitude extreme value and the associated data point
Determining the phase corresponding to each angle value based on the amplitude and each angle value in the time sequence chart, and determining the phase corresponding to each angle value based on each phaseGenerating data points
A corresponding one of the polar coordinate points.
In one implementation manner, the step S30114 specifically includes the following steps:
inputting the amplitude values, the maximum amplitude value and the minimum amplitude value of the plurality of angles corresponding to the associated data points in sequence into a target calculation formula to obtain the phases corresponding to the plurality of polar coordinate points in the polar coordinate point set corresponding to the data point;
the target calculation formula is as follows:
wherein the content of the first and second substances,
in order to be the amplitude value,
in order to be the phase position,
for the maximum value of the amplitude value,
is the minimum value of the amplitude, t is the target value,
g is a preset fixed value for one of the angles.
For example, assume that several angles include
，
，
，
And t =10, the time series diagram shown in fig. 2 will be transformed into the polar diagram shown in fig. 3, which shows a rotationally symmetric petal shape.
As shown in fig. 1, the method further comprises the steps of:
and S400, inputting the battery characteristic data corresponding to the moments into a target deep learning prediction model to obtain a second prediction state corresponding to the target bidirectional lithium ion battery.
In short, the target neural network model is a machine learning model under deep supervised learning, and the target deep learning prediction model is a machine learning model under unsupervised learning. In the embodiment, two different types of machine learning models are adopted to jointly predict the battery state of the target bidirectional lithium ion battery, so that the prediction deviation caused by a single model can be avoided, and the accuracy of battery state prediction is improved. Specifically, in this embodiment, a target deep learning model is trained in advance, and the battery characteristic data at each time is input into the target deep learning prediction model, so as to obtain the second prediction state of the target bidirectional lithium ion battery.
In one implementation, the target neural network model and the target deep learning prediction model are respectively trained in advance through a target training data set, the target training data set includes an original training data set and an augmented training data set, and the augmented training data set is obtained by generating an antagonistic network according to the original training data set and the DCGAN deep convolution. According to the embodiment, the polar coordinate graph after feature extraction is subjected to data expansion by using the DCGAN, so that a large amount of data is obtained, and the problem of insufficient imbalance of fault data is solved. The target training data set containing sufficient data can increase the classification accuracy of the model and solve the problem of robustness of the model.
In an implementation manner, the first prediction state/the second prediction state is one of an initial period, a healthy period, a decline period, and a discard period, where the remaining charge and discharge times corresponding to the initial period, the healthy period, the decline period, and the discard period respectively decrease sequentially.
As shown in fig. 1, the method further comprises the steps of:
and S500, determining the corresponding predicted service life of the target bidirectional lithium ion battery according to the first predicted state and the second predicted state.
Specifically, since the first prediction state and the second prediction state are generated based on different types of machine learning models, respectively, in order to reduce the prediction deviation caused by a single model, the present embodiment uses the first prediction state and the second prediction state to comprehensively determine the current battery state of the target bidirectional lithium ion battery, so as to accurately predict the predicted life corresponding to the target bidirectional lithium ion battery.
In one implementation, the predicted lifetime is a target remaining charge and discharge number, and the step S500 specifically includes the following steps:
step S501, determining a first residual charge and discharge frequency corresponding to the target bidirectional lithium ion battery according to the first prediction state;
step S502, determining a second residual charge and discharge frequency corresponding to the target bidirectional lithium ion battery according to the second prediction state;
and step S503, determining the target residual charge and discharge frequency according to the first residual charge and discharge frequency and the second residual charge and discharge frequency.
In brief, in this embodiment, the remaining charge and discharge frequency of the target bidirectional lithium ion battery is defined as the target remaining charge and discharge frequency, and the target remaining charge and discharge frequency is used to define the battery life of the target bidirectional lithium ion battery. Specifically, since the first prediction state and the second prediction state are generated based on different types of machine learning models, in order to reduce prediction deviation caused by a single model, the present embodiment determines the remaining charge and discharge number of the battery based on the first prediction state, that is, the first remaining charge and discharge number, and then determines the remaining charge and discharge number of the battery in the second prediction state, that is, the second remaining charge and discharge number. And finally, comprehensively judging the target residual charge and discharge frequency corresponding to the target bidirectional lithium ion battery based on the first residual charge and discharge frequency and the second residual charge and discharge frequency, so as to obtain the predicted service life of the target bidirectional lithium ion battery.
In one implementation, the step S503 specifically includes the following steps:
and determining the target residual charge and discharge times according to the average value of the first residual charge and discharge times and the second residual charge and discharge times.
In another implementation manner, the step S503 specifically includes the following steps:
obtaining model accuracies respectively corresponding to the target neural network model and the target deep learning prediction model;
determining weight values respectively corresponding to the target neural network model and the target deep learning prediction model according to model accuracies respectively corresponding to the target neural network model and the target deep learning prediction model;
and carrying out weighted average according to the weight values, the first residual charge and discharge times and the second residual charge and discharge times respectively corresponding to the target neural network model and the target deep learning prediction model to obtain the target residual charge and discharge times.
In one implementation mode, a digital twinning technology can be used to simulate the real charge and discharge process of the target bidirectional lithium ion battery in a virtual world based on a data-driven model, so that a plurality of battery characteristic data corresponding to the target bidirectional lithium ion battery can be acquired and monitored in real time.
In one implementation mode, the predicted service life and the state of the target bidirectional lithium ion battery can be displayed in a digital twin virtual world, the charge and discharge remaining times are visualized, the human-computer interaction efficiency is enhanced, and the reliability of a digital twin system is enhanced.
Based on the foregoing embodiment, the present invention further provides a device for predicting lifetime and estimating state of a bidirectional lithium ion battery, as shown in fig. 4, the device includes:
the data acquisition module 01 is used for acquiring battery characteristic data respectively corresponding to a target bidirectional lithium ion battery at a plurality of moments in a continuous time period;
determining time sequence data corresponding to the target bidirectional lithium ion battery according to the battery characteristic data respectively corresponding to the plurality of moments;
the first prediction module 02 is used for inputting the time series data into a target neural network model to obtain a first prediction state corresponding to the target bidirectional lithium ion battery;
the second prediction module 03 is configured to input the battery characteristic data corresponding to the plurality of moments into a target deep learning prediction model to obtain a second prediction state corresponding to the target bidirectional lithium ion battery;
and the service life predicting module 04 is used for determining the predicted service life corresponding to the target bidirectional lithium ion battery according to the first predicted state and the second predicted state.
Based on the above embodiments, the present invention further provides a terminal, and a schematic block diagram thereof may be as shown in fig. 5. The terminal comprises a processor, a memory, a network interface and a display screen which are connected through a system bus. Wherein the processor of the terminal is configured to provide computing and control capabilities. The memory of the terminal comprises a nonvolatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of an operating system and computer programs in the non-volatile storage medium. The network interface of the terminal is used for connecting and communicating with an external terminal through a network. The computer program is executed by a processor to implement a method for lifetime prediction and state estimation of a bi-directional lithium ion battery. The display screen of the terminal can be a liquid crystal display screen or an electronic ink display screen.
It will be appreciated by those skilled in the art that the block diagram of fig. 5 is only a block diagram of a portion of the structure associated with the inventive arrangements and does not constitute a limitation of the terminal to which the inventive arrangements are applied, and that a particular terminal may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one implementation, one or more programs are stored in a memory of the terminal and configured to be executed by one or more processors, including instructions for performing a method of lifetime prediction and state estimation for a bi-directional lithium ion battery.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, databases or other media used in the embodiments provided herein may include non-volatile and/or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), rambus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
In summary, the present invention discloses a method for predicting a lifetime and estimating a state of a bi-directional lithium ion battery, wherein the method comprises the steps of obtaining battery characteristic data corresponding to a target bi-directional lithium ion battery at a plurality of times within a continuous time period; determining time sequence data corresponding to the target bidirectional lithium ion battery according to the battery characteristic data respectively corresponding to the plurality of moments; inputting the time sequence data into a target neural network model to obtain a first prediction state corresponding to the target bidirectional lithium ion battery; inputting the battery characteristic data corresponding to the moments into a target deep learning prediction model to obtain a second prediction state corresponding to the target bidirectional lithium ion battery; and determining the corresponding predicted service life of the target bidirectional lithium ion battery according to the first predicted state and the second predicted state. The invention predicts the battery life of the bidirectional lithium ion battery by combining the neural network model and the deep learning model, and solves the problems that the battery life is determined according to manual experience analysis in the prior art, a large amount of labor cost is required to be consumed, and the judgment result is inaccurate due to subjectivity.
It is to be understood that the invention is not limited to the examples described above, but that modifications and variations may be effected thereto by those of ordinary skill in the art in light of the foregoing description, and that all such modifications and variations are intended to be within the scope of the invention as defined by the appended claims.
Claims (10)
1. A method for predicting the service life and estimating the state of a bidirectional lithium ion battery is characterized by comprising the following steps:
acquiring battery characteristic data respectively corresponding to a target bidirectional lithium ion battery at a plurality of moments in a continuous time period;
determining time sequence data corresponding to the target bidirectional lithium ion battery according to the battery characteristic data respectively corresponding to the plurality of moments;
inputting the time sequence data into a target neural network model to obtain a first prediction state corresponding to the target bidirectional lithium ion battery;
inputting the battery characteristic data corresponding to the moments into a target deep learning prediction model to obtain a second prediction state corresponding to the target bidirectional lithium ion battery;
and determining the corresponding predicted service life of the target bidirectional lithium ion battery according to the first predicted state and the second predicted state.
2. The method according to claim 1, wherein the time-series data is a time-series diagram, the abscissa of the time-series diagram is time, and the ordinate of the time-series diagram is amplitude; the time series diagram comprises a plurality of data points, the data points correspond to the moments one by one, the abscissa corresponding to each data point is determined based on the moment corresponding to the data point, and the ordinate corresponding to each data point is determined based on the battery characteristic data at the moment corresponding to the data point.
3. The method of claim 2, wherein the target neural network model comprises a feature extraction module and a classification module, and the step of inputting the time-series data into the target neural network model to obtain the first predicted state corresponding to the target bi-directional lithium ion battery comprises:
inputting the time series diagram into the feature extraction module to obtain a polar coordinate diagram corresponding to the time series diagram, wherein the polar coordinate diagram comprises a plurality of polar coordinate points, and the polar coordinate points correspond to the data points one by one;
and inputting the polar coordinate graph into the classification module to obtain the first prediction state.
4. The method of claim 3, wherein the inputting the time-series diagram into the feature extraction module to obtain a polar coordinate diagram corresponding to the time-series diagram comprises:
inputting the time series diagram into the feature extraction module, and determining polar coordinate point sets corresponding to the data points respectively through the feature extraction module, wherein each polar coordinate point set comprises a plurality of polar coordinate points, and each polar coordinate point in the same polar coordinate point set is in a rotational symmetry relationship;
and determining the polar coordinate graph according to the polar coordinate point sets respectively corresponding to the data points.
5. The method of claim 4, wherein the determining the set of polar coordinate points corresponding to each data point comprises:
obtaining the maximum amplitude value and the minimum amplitude value corresponding to the time series diagram;
acquiring a preset target value, and determining an associated data point corresponding to each data point according to the target value;
acquiring a plurality of preset angles, wherein the angles are sequentially increased or decreased by preset angle values;
and determining the phases of a plurality of polar coordinate points corresponding to the data point according to the plurality of angles, the amplitude corresponding to the associated data point, the maximum amplitude value and the minimum amplitude value, wherein the phases corresponding to the plurality of polar coordinate points respectively correspond to the plurality of angles in a one-to-one manner.
6. The method of claim 5, wherein determining the phase of the polar coordinate points corresponding to the data point according to the angles, the amplitude corresponding to the associated data point, the maximum amplitude value, and the minimum amplitude value comprises:
inputting the amplitude values, the maximum amplitude value and the minimum amplitude value of the plurality of angles corresponding to the associated data points in sequence into a target calculation formula to obtain the phases corresponding to the plurality of polar coordinate points in the polar coordinate point set corresponding to the data point;
the target calculation formula is as follows:
wherein, the first and the second end of the pipe are connected with each other,
is the amplitude of the received signal and is,
is the phase of the signal to be detected,
for the maximum value of the amplitude value,
is the minimum value of the amplitude, t is the target value,
g is a preset fixed value for one of the angles.
7. The method of claim 1, wherein the predicting the life time is a target remaining charge/discharge number, and the determining the predicted life time corresponding to the target bi-directional lithium ion battery according to the first predicted state and the second predicted state comprises:
determining a first residual charge and discharge frequency corresponding to the target bidirectional lithium ion battery according to the first prediction state;
determining a second residual charge and discharge frequency corresponding to the target bidirectional lithium ion battery according to the second prediction state;
and determining the target residual charge and discharge frequency according to the first residual charge and discharge frequency and the second residual charge and discharge frequency.
8. An apparatus for predicting lifetime and estimating state of a bi-directional lithium ion battery, the apparatus comprising:
the data acquisition module is used for acquiring battery characteristic data respectively corresponding to a target bidirectional lithium ion battery at a plurality of moments in a continuous time period;
determining time sequence data corresponding to the target bidirectional lithium ion battery according to the battery characteristic data respectively corresponding to the plurality of moments;
the first prediction module is used for inputting the time sequence data into a target neural network model to obtain a first prediction state corresponding to the target bidirectional lithium ion battery;
the second prediction module is used for inputting the battery characteristic data corresponding to the moments into a target deep learning prediction model to obtain a second prediction state corresponding to the target bidirectional lithium ion battery;
and the service life prediction module is used for determining the predicted service life corresponding to the target bidirectional lithium ion battery according to the first prediction state and the second prediction state.
9. A terminal, comprising a memory and one or more processors; the memory stores one or more programs; the program comprises instructions for performing a method of lifetime prediction and state estimation of a bi-directional lithium ion battery according to any of claims 1-7; the processor is configured to execute the program.
10. A computer-readable storage medium having stored thereon a plurality of instructions adapted to be loaded and executed by a processor to perform the steps of the method for predicting lifetime and estimating state of a bi-directional lithium ion battery as set forth in any one of claims 1-7.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211205391.1A CN115267558A (en) | 2022-09-30 | 2022-09-30 | Service life prediction and state estimation method of bidirectional lithium ion battery |
| PCT/CN2022/138134 WO2024066055A1 (en) | 2022-09-30 | 2022-12-09 | Service life prediction and state estimation method for bidirectional lithium ion battery |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211205391.1A CN115267558A (en) | 2022-09-30 | 2022-09-30 | Service life prediction and state estimation method of bidirectional lithium ion battery |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115267558A true CN115267558A (en) | 2022-11-01 |
Family
ID=83758008
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211205391.1A Pending CN115267558A (en) | 2022-09-30 | 2022-09-30 | Service life prediction and state estimation method of bidirectional lithium ion battery |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN115267558A (en) |
| WO (1) | WO2024066055A1 (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115856694A (en) * | 2022-12-28 | 2023-03-28 | 深圳市南霸科技有限公司 | Battery life prediction method and device, computer equipment and storage medium |
| CN117688850A (en) * | 2024-02-03 | 2024-03-12 | 深圳三晖能源科技有限公司 | Outdoor energy storage battery life prediction method, system, equipment and storage medium |
| WO2024066055A1 (en) * | 2022-09-30 | 2024-04-04 | 深圳先进技术研究院 | Service life prediction and state estimation method for bidirectional lithium ion battery |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110222431A (en) * | 2019-06-11 | 2019-09-10 | 哈尔滨工业大学 | The lithium ion battery residual life prediction technique merged based on gating cycle unit neural network and Kalman filter model |
| CN112765772A (en) * | 2020-12-25 | 2021-05-07 | 武汉理工大学 | Power battery residual life prediction method based on data driving |
| CN114004134A (en) * | 2021-08-27 | 2022-02-01 | 中国航空工业集团公司上海航空测控技术研究所 | Digital full-automatic aircraft storage battery life prediction method |
| CN114372417A (en) * | 2022-01-12 | 2022-04-19 | 青岛科技大学 | Electric vehicle battery health state and remaining life evaluation method based on charging network |
| CN114755586A (en) * | 2022-04-27 | 2022-07-15 | 电子科技大学 | Lithium ion battery residual life prediction method |
| CN114924203A (en) * | 2022-05-24 | 2022-08-19 | 上海电享信息科技有限公司 | Battery SOH prediction analysis method and electric automobile |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10401433B2 (en) * | 2015-01-21 | 2019-09-03 | Samsung Electronics Co., Ltd. | Method and apparatus for estimating battery life |
| CN104852686A (en) * | 2015-05-27 | 2015-08-19 | 中国人民解放军国防科学技术大学 | Solar cell life prediction method based on current attenuation |
| CN110133524B (en) * | 2019-04-19 | 2022-07-08 | 丰翼科技(深圳)有限公司 | Battery charge state calculation method, device, server and medium |
| CN112348185A (en) * | 2020-11-04 | 2021-02-09 | 上海海事大学 | Lithium battery residual life prediction method based on variational modal decomposition and integrated depth model |
| CN115267558A (en) * | 2022-09-30 | 2022-11-01 | 深圳先进技术研究院 | Service life prediction and state estimation method of bidirectional lithium ion battery |
-
2022
- 2022-09-30 CN CN202211205391.1A patent/CN115267558A/en active Pending
- 2022-12-09 WO PCT/CN2022/138134 patent/WO2024066055A1/en unknown
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110222431A (en) * | 2019-06-11 | 2019-09-10 | 哈尔滨工业大学 | The lithium ion battery residual life prediction technique merged based on gating cycle unit neural network and Kalman filter model |
| CN112765772A (en) * | 2020-12-25 | 2021-05-07 | 武汉理工大学 | Power battery residual life prediction method based on data driving |
| CN114004134A (en) * | 2021-08-27 | 2022-02-01 | 中国航空工业集团公司上海航空测控技术研究所 | Digital full-automatic aircraft storage battery life prediction method |
| CN114372417A (en) * | 2022-01-12 | 2022-04-19 | 青岛科技大学 | Electric vehicle battery health state and remaining life evaluation method based on charging network |
| CN114755586A (en) * | 2022-04-27 | 2022-07-15 | 电子科技大学 | Lithium ion battery residual life prediction method |
| CN114924203A (en) * | 2022-05-24 | 2022-08-19 | 上海电享信息科技有限公司 | Battery SOH prediction analysis method and electric automobile |
Non-Patent Citations (1)
| Title |
|---|
| 张玲玲 等: "《柴油发动机故障诊断技术》", 31 December 2015 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2024066055A1 (en) * | 2022-09-30 | 2024-04-04 | 深圳先进技术研究院 | Service life prediction and state estimation method for bidirectional lithium ion battery |
| CN115856694A (en) * | 2022-12-28 | 2023-03-28 | 深圳市南霸科技有限公司 | Battery life prediction method and device, computer equipment and storage medium |
| CN115856694B (en) * | 2022-12-28 | 2023-10-31 | 深圳市南霸科技有限公司 | Battery life prediction method, device, computer equipment and storage medium |
| CN117688850A (en) * | 2024-02-03 | 2024-03-12 | 深圳三晖能源科技有限公司 | Outdoor energy storage battery life prediction method, system, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2024066055A1 (en) | 2024-04-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115267558A (en) | Service life prediction and state estimation method of bidirectional lithium ion battery | |
| CN111210024B (en) | Model training method, device, computer equipment and storage medium | |
| Chen et al. | Gated recurrent unit based recurrent neural network for remaining useful life prediction of nonlinear deterioration process | |
| US20230366936A1 (en) | Lithium ion battery lifetime prediction method, discharge capacity retention rate prediction method, lifetime prediction program, discharge capacity retention rate prediction program, and information processing device | |
| CN115310562B (en) | Fault prediction model generation method suitable for energy storage equipment in extreme state | |
| CN115356639B (en) | Intelligent health monitoring method and system for bidirectional lithium ion battery | |
| CN114492211B (en) | Residual oil distribution prediction method based on autoregressive network model | |
| CN116380166A (en) | Equipment abnormality monitoring method, electronic equipment and storage medium | |
| US11423321B2 (en) | Method and system for predicting system status | |
| CN111401472B (en) | Infrared target classification method and device based on deep convolutional neural network | |
| CN116089870A (en) | Industrial equipment fault prediction method and device based on meta-learning under small sample condition | |
| EP3904987B1 (en) | Control support apparatus, control support method, control support program, computer readable medium with control support program recorded thereon and control system | |
| CN110334816A (en) | A kind of industrial equipment detection method, device, equipment and readable storage medium storing program for executing | |
| EP3128296B1 (en) | Measurement value analysis device and measurement value analysis method | |
| CN111881023A (en) | Software aging prediction method and device based on multi-model comparison | |
| CN111445105B (en) | Power plant online performance diagnosis method and system based on target value analysis | |
| CN110232130B (en) | Metadata management pedigree generation method, apparatus, computer device and storage medium | |
| CN114547145A (en) | Method, system, storage medium and equipment for detecting time sequence data abnormity | |
| US20190042681A1 (en) | Method and apparatus for selecting integrated circuit device neural network modeling sample | |
| CN111753461A (en) | Tidal water level correction method, target residual water level acquisition method, device and equipment | |
| CN117052970A (en) | Intelligent control system and method for pneumatic ball valve assembly | |
| CN115147349A (en) | Method and device for determining smelting end point of converter, electronic equipment and storage medium | |
| CN114192583A (en) | Scada platform-based strip steel rolling process quality monitoring method and system | |
| CN112925271A (en) | Data processing method, automatic control method and device | |
| CN113994276A (en) | Method for verifying system parameters of an energy system, method for operating an energy system, and energy management system for an energy system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20221101 |