Method and system for predicting the degradation state of an electric battery

Abstract

The present invention relates to a method (100) for predicting the degradation state of at least one electric battery, said method (100) comprising at least: A first step of collecting (110) at least one piece of information relating to an initial cycling protocol; A step of selecting (120) at least one predictive cycling protocol; A second step of collecting (130) at least one data point relating to at least one set of parameters; A processing step (140) of said at least one piece of information, said at least one data point, and the predictive cycling protocol, comprising: A calculation step (141) of at least one descriptor; A classification step (142) of the degradation state; A calculation step (143) of the evolution of said degradation state; A step of obtaining (144) a calculated state of degradation of said electric battery. Fig. 1

Description

Title of the invention: Method and system for predicting the state of degradation of an electric battery Technical field

[0001] The present invention relates to the field of electric batteries. It finds a particularly advantageous application in the field of predicting the state of degradation of an electric battery. STATE OF THE ART

[0002] The development of electric batteries, such as high-performance lithium-ion batteries, is a crucial area of ​​research, particularly in the context of electric vehicles (EVs) where battery longevity and efficiency have a direct impact on the vehicle's overall driving range and performance. However, aging of the electric battery, and particularly lithium-ion batteries (LiBs), is a complex process that can have a significant impact on battery performance and lifetime, making it an important consideration in the design and operation of LiBs.

[0003] The aging process of LiBs is influenced by several factors, including cycling protocols and storage conditions. Therefore, it is difficult to accurately predict the aging process and develop effective strategies to mitigate it. Experimental studies on LiB aging are generally very time-consuming and expensive.

[0004] An object of the present invention is therefore to propose a faster and more economical solution to predicting the evolution of the state of degradation of an electric battery.

[0005] Other objects, features and advantages of the present invention will become apparent from the following description and accompanying drawings. It is understood that other advantages may be incorporated.

[0006] SUMMARY

[0007] The present invention relates to a method for predicting the state of degradation of at least one electric battery, preferably for an electric vehicle, said method being configured to be executed by at least one electronic system, preferably said electronic system being configured to communicate with at least one database and / or at least one set of sensors, said method comprising at least: a. A first collection step, preferably executed by at least one first collection module of said electronic system, of at least one in training relating to an initial cycling protocol, preferably said initial cycling protocol corresponding to the current cycling protocol of said electric battery, said initial cycling protocol being taken from at least the following plurality of cycling protocols: i. A first cycling protocol, said first cycling protocol being a constant current and constant voltage cycling protocol; ii. A second cycling protocol, said second cycling protocol being a pulsed current cycling protocol; iii. A third cycling protocol, said third cycling protocol being a multi-stage current cycling protocol; b. A selection step, preferably executed by at least one selection module of said electronic system, of at least one prediction cycling protocol taken from said plurality of cycling protocols; c. A second step of collecting, preferably executed by at least one second collection module of said electronic system, at least one piece of data relating to at least one set of parameters, said set of parameters comprising at least one of the following parameters: i. An initial state of charge of the electric battery; ii. A final state of charge of the electric battery; iii. A number N of charge-discharge cycles of said battery; iv. A temperature T of the electric battery; v. A charging rate C, i.e. a charging speed, associated with at least one cycling protocol taken from at least said plurality of cycling protocols; d. A processing step, preferably executed by at least one calculation module of said electronic system, by automatic learning from at least one pre-trained mathematical model, said at least one piece of information, said at least one piece of data and the prediction cycling protocol, said processing step comprising at least: i. A step of calculating at least one descriptor by applying said pre-trained mathematical model in a multidimensional calculation space, said multidimensional calculation space being configured so that each parameter of said set of parameters defines a dimension of said multidimensional calculation space; ii. A step of classifying the state of degradation from said descriptor relative to a set of predetermined classes; iii. A step of calculating the temporal evolution of said state of de- gradation of said electric battery, by calculating a plurality of degradation states of said electric battery, as a function of at least one variable, said variable being taken from at least: A. An initial state of charge of the electric battery; B. A final state of charge of the electric battery; C. Pressure applied to at least part of the electric battery; D. A number N' of charge-discharge cycles of said electric battery; E. A temperature T' of the electric battery; F. A first charge rate Cl relative to the first cycling protocol; G. A second charge rate C2 relative to the second cycling protocol; H. A third C3 charge rate relative to the third cycling protocol; I. A first DI discharge rate relative to the first cycling protocol; J. A second discharge rate D2 relative to the second cycling protocol; K. A third discharge rate D3 relative to the third cycling protocol; L. A load limit; M. A pause time at zero current; N. Another cycling protocol; iv. A step of obtaining a calculated state of the degradation of said electric battery, said calculated state comprising at least one predictive mathematical model, said predictive mathematical model being configured to mathematically represent the evolution of the state of degradation of said electric battery as a function of at least said variable.

[0008] The present invention cleverly uses a mathematical model pre-trained on data from various electric batteries to generate a predictive mathematical model specific to a given electric battery. This allows for considerable time and system resource savings because it is then not necessary to rebuild a mathematical model from scratch.

[0009] The present invention makes it possible to improve the quality and reliability of electric batteries. One of the numerous applications of the present invention is to help electric battery manufacturers to improve the quality and reliability of their batteries by reducing the number of premature failures.

[0010] The present invention makes it possible to optimize the production parameters of an electric battery. Indeed, the manufacturer can use the results of a prediction to adjust the production parameters in order to slow down the degradation of the battery and thus improve the quality of the battery without relying on cycling tests, which can be both time-consuming and expensive. The present invention is simple and easy to implement and makes it possible to produce rapid results, which leads to cost savings and improved efficiency in the production of electric batteries.

[0011] The present invention makes it possible to reduce the environmental impact of electric batteries. Indeed, by extending the life of electric batteries, the number of electric batteries required can thus be reduced, thereby reducing the environmental impact of the production and disposal of electric batteries.

[0012] Furthermore, the present invention allows optimization of the management of an electric battery. Indeed, by using the results of the prediction of the evolution of the state of degradation of an electric battery, a user can then optimize the management of the electric battery by adjusting the cycling and / or storage conditions, for example without limitation, to extend the life of the electric battery and avoid premature degradation.

[0013] In addition, the present invention makes it possible to plan the maintenance and repairs of electric batteries. Indeed, by anticipating the degradation of the electric battery, a user can plan maintenance and repairs accordingly, which can reduce costs and improve the availability of electric batteries.

[0014] Finally, the present invention makes it possible to improve the energy efficiency of the electric battery sector. Indeed, by extending the life of an electric battery, a user can thus reduce the frequency of replacement of the electric battery, which can reduce energy consumption and improve the energy efficiency of the sector.

[0015] The present invention also relates to a computer program product, preferably recorded on a non-transitory memory medium, comprising instructions, which when carried out by at least one of a processor, a computer, executes the method according to the present invention.

[0016] The present invention also relates to a non-transitory memory medium comprising a computer program product according to the present invention.

[0017] The present invention also relates to an electronic system configured to execute a method according to the present invention, said electronic system comprising at least: a. A communication module configured to communicate with at least a database and / or at least one set of sensors; b. A first collection module configured to collect, preferably via the communication module, information relating to the initial cycling protocol of the electric battery; c. A selection module configured to select at least one prediction cycling protocol from a plurality of cycling protocols; d. A second collection module configured to collect, preferably via the communication module, data relating to a set of parameters; e. A calculation module configured to: i. Processing by machine learning from at least one pre-trained mathematical model, said at least one piece of information, said at least one piece of data and a prediction cycling protocol; ii. Compute at least one descriptor by applying said pre-trained mathematical model in a multidimensional computational space; iii. Classify the state of degradation of said electric battery from said descriptor relative to a set of predetermined classes; iv. Calculate the temporal evolution of said state of degradation of said electric battery, by calculating a plurality of states of degradation of said electric battery, as a function of at least one variable, said variable being taken from at least: A. An initial state of charge of the electric battery; B. A final state of charge of the electric battery; C. Pressure applied to at least part of the electric battery; D. A number N' of charge-discharge cycles of said electric battery; E. A temperature T' of the electric battery; F. A first charge rate Cl relative to the first cycling protocol; G. A second charge rate C2 relative to the second cycling protocol; H. A third C3 charge rate relative to the third cycling protocol; I. A first DI discharge rate relative to the first cycling protocol; J. A second discharge rate D2 relative to the second cycling protocol; K. A third discharge rate D3 relative to the third cycling protocol; L. A load limit; M. A pause time at zero current; N. Another cycling protocol; v. Generate at least one predictive mathematical model, said predictive mathematical model being configured to mathematically represent the evolution of the state of degradation of said electric battery as a function of at least said variable.

[0018] In particular, during the development of the present invention, a machine learning mathematical model capable of classifying aging conditions based on the degradation rate of a LiB was developed. This model was designed using a real data set from a manufacturer of electric batteries for electric vehicles. This development work made it possible to identify the patterns and relationships between the aging process and different factors in a large multi-parameter space. A pre-trained mathematical model was thus designed to predict the degradation rate of LiBs under different cycle conditions. The present invention has generated very interesting results making it possible to effectively monitor and mitigate battery aging in electric vehicles.

[0019] It will simply be recalled here that machine learning methods make it possible to take advantage of large quantities of data to identify models and relationships between various factors and, for example, the aging process of an electric battery. This type of pre-trained model thus makes it possible, from data specific to a given electric battery, to predict the evolution of its state of degradation as a function of various variables via the generation of a new predictive mathematical model specific to said electric battery.

[0020] Thus, the prior art, in particular the article “Joint modeling for early predictions of Li-ion battery cycle life and degradation trajectory” (Energy, Volume 277, (2023), 127633, ISSN 0360-5442, by Zhang Chen, Liqun Chen, Zhengwei Ma, Kangkang Xu, Yu Zhou, Wenjing Shen), discloses the general principle of using machine learning methods to make estimates and predictions related to the life cycle and the evolution of the degradation of a Li-ion battery. However, the methods of the prior art still lack precision and reliability. BRIEF DESCRIPTION OF THE FIGURES

[0021] The aims, objects, as well as the characteristics and advantages of the invention will emerge more clearly from the detailed description of an embodiment of the latter which is illustrated by the following accompanying drawings in which:

[0022] [Fig.l] [Fig.l] represents a prediction method according to an embodiment of the present invention.

[0023] [Fig.2] [Fig.2] represents an electronic prediction system according to an embodiment of the present invention.

[0024] [Fig.3] [Fig.3] represents a feedback loop for controlling the electric battery management system according to an embodiment of the present invention.

[0025] [Fig.4] [Fig.4] represents the obtaining of a decision support graph within the framework of an embodiment of the present invention.

[0026] The drawings are given as examples and are not limiting of the invention. They constitute schematic representations of principle intended to facilitate the understanding of the invention and are not necessarily on the scale of practical applications. In particular, the dimensions are not representative of reality. DETAILED DESCRIPTION

[0027] Before beginning a detailed review of embodiments of the invention, optional features which may possibly be used in combination or alternatively are set out below:

[0028] According to one example, the present invention comprises at least one step of displaying, by at least one display module of said electronic system, at least one graphical representation of said predictive mathematical model.

[0029] According to one example, the present invention comprises at least one step of interaction by a user with said predictive mathematical model via a user interface of said electronic system.

[0030] According to one example, the present invention comprises at least one step of retroactive control, preferably by at least one electric battery management system, of at least one variable as a function of said predictive mathematical model and / or at least one predetermined setpoint.

[0031] According to one example, the retroactive piloting step is carried out in real time.

[0032] According to one example, at least one of the first collection step respectively and the second collection step comprises the acquisition respectively of said information and said data from at least one database and / or at least one set of sensors.

[0033] According to one example, the present invention comprises: a. at least one display module configured to display at least one graphical representation of said mathematical model, and b. at least one user interface configured to allow at least one interaction by a user with said predictive mathematical model.

[0034] Furthermore, the following description listing the principles, aspects, and implementations of the present invention, as well as specific examples thereof, is intended to encompass both their structural and functional equivalents, whether presently known or developed in the future. Thus, for example, it will be appreciated by those skilled in the art that all block diagrams herein represent conceptual views of illustrative circuits incorporating the principles of the present invention. Similarly, it will be understood that all flowcharts, and the like, represent various processes that may be substantially represented on computer-readable media and thereby executed by a computer or processor, whether or not that computer or processor is explicitly shown.

[0035] The functions of the various elements shown in the figures, including any functional block referred to as a "processor" or "module", may be provided by the use of dedicated hardware as well as hardware capable of executing software in association with an appropriate computer program or instructions. When provided by a processor, the instructions may be provided by a single dedicated processor, by a single shared processor, or by a plurality of individual processors, some of which may be shared. In some embodiments of the present invention, the processor may be a general-purpose processor, such as a central processing unit (CPU), for example.Furthermore, the explicit use of the term "processor" should not be interpreted as referring exclusively to hardware capable of executing software and may implicitly include, but is not limited to, an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), a read-only memory (ROM) for storing software, random access memory (RAM), and non-volatile storage. Other hardware, conventional and / or custom, may also be included.

[0036] Software modules, or simply modules that are assumed to be software, may be represented herein as any combination of flowchart elements or other elements indicating the execution of process steps and / or a textual description. Such modules may be executed by hardware that is expressly or implicitly represented. Furthermore, it is to be understood that the module may include for example, but not limited to, computer program logic, computer program instructions, software, firmware, hardware circuitry, or a combination thereof that provides the required capabilities.

[0037] The present invention proposes to use a machine learning model to classify the aging cycling conditions according to the degradation rate of electric batteries and in particular Li-ion (LiB) batteries, and to generate a predictive mathematical model configured to predict the evolution over time of the state of health of a given electric battery according to various variables and / or parameters. It should be noted that in the remainder of the description the terms “electric battery”, “Li-ion battery” or “LiB” are interpreted identically.

[0038] Cleverly, the present invention uses a set of data from real conditions of use of electric batteries operating under various conditions to identify the relationships between the aging process and different factors in a vast multi-parameter space. In particular, the present invention can be applied to the automotive field in a non-limiting manner.

[0039] As presented below, the present invention makes it possible to predict the degradation rate of an electric battery, preferably of the Li-ion type, under different cycle / storage conditions.

[0040] Unexpectedly, the present invention makes it possible to identify the different factors that influence the aging process of an electric battery. The significant correlations observed during the development of the present invention make it possible to determine which variables have the most significant impact on the degradation rate of an electric battery.

[0041] These variables may correspond to specific aging mechanisms, and the results are essential for optimizing the designs of battery management systems capable of effectively monitoring and limiting the aging of an electric battery in electric vehicles, for example without limitation. The present invention allows for improved performance, greater reliability and the resolution of durability problems of the electric battery of a vehicle, for example without limitation.

[0042] The present invention provides a valuable tool for predicting, by at least one predictive mathematical model, the performance and lifetime of electric batteries, preferably Li-ion, advantageously in electric vehicles, under different cycle and storage conditions. The ability to identify factors that influence battery aging and predict its effects can lead to significant improvements in battery design and use, ultimately contributing to the development of more efficient and sustainable electric vehicles.

[0043] Furthermore, the present invention finds a very clever application in the control, in the form of a feedback loop for example, of the battery management system known as BMS, from the English acronym “Battery Management System”.

[0044] Indeed, for example, by providing predictions of the state of degradation of the electric battery in real time, the present invention allows intelligent control of the BMS.

[0045] Indeed, for example, by monitoring, regularly and / or permanently, the cycling conditions of the battery and by entering the data in the present invention, i.e. in a mathematical model being configured to represent mathematics. matically the evolution of the state of degradation of said battery, the BMS battery management system can use the generated mathematical model to predict the state of degradation of the electric battery according to various parameters and thus can adjust at least some of these parameters, such as for example the charging and discharging parameters of the electric battery. This can help to optimize the life of the electric battery and reduce the risk of premature failure.

[0046] Furthermore, the present invention can also assist the BMS in planning maintenance and repair schedules based on the calculated and thus predicted degradation rate. By planning maintenance and repairs in advance, the BMS can reduce the risk of unexpected failures and minimize downtime.

[0047] Thus, according to a preferred embodiment, the present invention relates to a method for predicting the state of degradation of at least one electric battery. Said electric battery being for example configured to cooperate with an electric vehicle.

[0048] The method according to the present invention is advantageously configured to be executed by at least one electronic system. This electronic system, called a prediction system, is preferably configured to communicate with at least one database and / or at least a first set of sensors as described below.

[0049] According to one embodiment, and as illustrated by [Fig.l], the method 100 for predicting the state of degradation of an electric battery 10 comprises at least: a. A first collection step 110, executed by at least one first collection module 210 of said electronic system 200, of at least one piece of information relating to an initial cycling protocol, also called initial charge / discharge protocol. Preferably, said initial cycling protocol corresponds to the current cycling protocol of said electric battery 10. As discussed below, the first initial cycling protocol is taken from at least the following plurality of cycling protocols: i. A first cycling protocol, said first cycling protocol being a constant current and constant voltage cycling protocol; ii. A second cycling protocol, said second cycling protocol being a pulsed current cycling protocol; iii. A third cycling protocol, said third cycling protocol being a multi-stage current cycling protocol; b. A selection step 120, executed by at least one selection module 220 of said electronic system 200, of at least one prediction cycling protocol from among said plurality of cycling protocols; Advantageously, two prediction cycling protocols can be se- selected; c. A second collection step 130, executed by at least one second collection module 230 of said electronic system 200, of at least one piece of data relating to at least one set of parameters, said set of parameters comprising at least one of the following parameters: i. An initial state of charge of the electric battery 10; ii. A final state of charge of the electric battery 10; iii. A number N of charge-discharge cycles of said battery 10; iv. A temperature T of the electric battery 10; v. A charging rate C, i.e. a charging speed, associated with at least one cycling protocol taken from at least said plurality of cycling protocols; d. A processing step 140, executed by at least one calculation module 240 of said electronic system 200, by automatic learning from at least one pre-trained mathematical model, said at least one piece of information, said at least one piece of data and said prediction cycling protocol. Advantageously, said processing step 140 comprises at least: i. A step 141 of calculating at least one descriptor by applying said pre-trained mathematical model in a multidimensional calculation space, said multidimensional calculation space being configured so that each parameter of said set of parameters defines a dimension of said multidimensional calculation space; ii. A step 142 of classifying the state of degradation from said descriptor relative to a set of predetermined classes; iii. A step 143 of calculating the temporal evolution of said state of degradation of said electric battery (10), by calculating a plurality of states of degradation of said electric battery, as a function of at least one variable, said variable being taken from at least: A. An initial state of charge of the electric battery 10; B. A final state of charge of the electric battery 10; C. A pressure applied to at least a portion of the electric battery 10, said pressure preferably being predetermined and advantageously fixed; D. A number N' of charge-discharge cycles of said electric battery 10; E. A temperature T' of the electric battery 10; F. A first charge rate Cl relative to the first cycling protocol; G. A second charge rate C2 relative to the second cycling protocol; H. A third C3 charge rate relative to the third cycling protocol; I. A first DI discharge rate relative to the first cycling protocol; J. A second discharge rate D2 relative to the second cycling protocol; K. A third discharge rate D3 relative to the third cycling protocol; L. A load limit; M. A pause time at zero current; N. Another cycling protocol; iv. A step 144 of obtaining a calculated state of the degradation of said electric battery 10, said calculated state comprising at least one predictive mathematical model, said predictive mathematical model being configured to mathematically represent the evolution of the state of degradation of said electric battery 10 as a function of at least said variable, preferably by variation of at least said variable.

[0050] This thus makes it possible to predict the state of degradation of the electric battery 10 as a function of the various variables.

[0051] Thus, the present invention makes it possible, from certain data of the electric battery, to generate a predictive mathematical model of the state of degradation of the electric battery 10. This predictive mathematical model then makes it possible to predict, by the generation of at least one predictive mathematical model, said state of degradation as a function of various variables, this making it possible to predict the state of degradation of the electric battery as a function of these various variables.

[0052] Advantageously, the predictive mathematical model is a linear and / or non-linear combination of the parameters, weighted or not, allowing a mathematical representation in a multidimensional space of the state of degradation of the electric battery 10.

[0053] According to one embodiment, the first collection step 110 is configured to determine the initial cycling protocol of the electric battery 10, i.e. its current protocol, i.e. the one currently applied to it or that was last applied to it. “Cycling protocol” means the process used to charging and discharging an electric battery 10, it may also be the process used to test and evaluate the performance, life and safety of an electric battery 10. Preferably, a cycling protocol involves a series of repeated charges and discharges.

[0054] According to one embodiment, we will consider three distinct charging protocols, however it will be noted that the present invention can perfectly be implemented for other types of charging protocols existing to date or not.

[0055] Thus, according to a non-limiting embodiment, the first collection step 110 makes it possible to collect at least one piece of data relating to the nature of the initial cycling protocol of an electric battery 10 considered. Advantageously, this initial cycling protocol corresponds to at least one of the following three protocols: i. A first cycling protocol, also known as a constant current and constant voltage (CC-CV) cycling protocol. Said first cycling protocol is a widely used protocol that involves initially charging the electric battery with a predetermined constant current until it reaches a predetermined voltage, and then switching to a predetermined constant voltage to complete the charging process. This first cycling protocol aims to balance the charging speed and voltage control to prevent overcharging. This first cycling protocol is commonly used in various applications and helps provide an efficient and controlled charge. ii. A second cycling protocol, also called a pulsed current cycling protocol. This second cycling protocol consists of applying short bursts of high current to the electric battery with intermediate rest periods, i.e., pause times (see for example the following article: “Lv, H., Huang, X. & Liu, Y. Analysis on puise charging-discharging strategies for improving capacity retention rates of lithium-ion batteries. lonics 26, 1749-1770 (2020).”). It is believed by the person skilled in the art that this charging technique improves the capacity of the electric battery, its performance and also reduces its degradation rate. iii. A third cycling protocol also called multi-stage current cycling protocol. This third cycling protocol is a more complex protocol than the previous two and involves several charging stages with different current levels (see for example the following article: “Romain Mathieu, Olivier Briat, Philippe Gyan, Jean-Michel Vinassa. Fast charging for electric vehicles applications: Numerical optimization of a multi-stage charging protocol for lithium-ion battery and impact on cycle life. Journal of Energy Storage, 2021, 40, pp. 102756.(10.1016 / j.est.202L102756). (hal-04087488)").

[0056] It will be noted that the cycling protocols previously described have a different impact on the state of degradation, and therefore health, of an electric battery 10 and in particular of a LiB. The present invention, during its development, has shown that this state of degradation is strongly correlated with the operating conditions of said electric battery 10.

[0057] Cleverly, each protocol can be characterized by several specific parameters. Thus, the degradation of the electric batteries 10 and in particular of the LiBs preferably depends on a large set of cycle parameters, i.e. charge-discharge cycle.

[0058] Then, the selection step 120 makes it possible to select a prediction cycling protocol, i.e. a cycling protocol which may be different from the initial cycling protocol and which will serve as a parameter for the future prediction. Thus, the user can decide to predict the degradation state of an electric battery 10 if the latter is subjected to a particular cycling protocol, i.e. selected.

[0059] Advantageously, the second collection step 130 makes it possible to collect at least one piece of data, and preferably a plurality of data, relating to at least one parameter, preferably to various parameters. This step makes it possible to collect information, data, on the initial state of the electric battery 10, on its current state. This data is then used to define the state of the electric battery 10.

[0060] We will now describe an example of parameters considered by the present invention, and in particular during the second collection step 130. These various parameters have been cleverly selected because they represent the parameters of an electric battery 10 which can have the greatest impact on the degradation rate thereof: a. The initial state of charge of the electric battery 10: The initial state of charge of the electric battery 10 corresponds to the quantity of electric charge that it holds in relation to its maximum capacity before carrying out a charge-discharge cycle, i.e. cycling; b. The final state of charge of the electric battery 10: The final state of charge of the electric battery 10 corresponds to the quantity of electric charge that it holds in relation to its maximum capacity after having carried out a charge-discharge cycle, i.e. cycling; c. The number N of charge-discharge cycles of said electric battery 10: The number N of charge / discharge cycles, i.e. cycling, is a parameter which can strongly impact the degradation of a LiB. Indeed, the higher this number, the higher the degradation rate of the battery. Indeed, the number of repeated cycles of a battery can lead to several degradation mechanisms reducing the capacity of the electric battery 10 and its performance over time; d. The temperature T of the electric battery 10: During the development of the present invention, it was observed that the operating temperature of the electric battery 10 can play an important role in understanding its degradation rate. For example, by varying the temperature within a specific range, it is possible to evaluate the performance and behavior of the electric battery 10 under different thermal conditions. e. The charging rate C: The charging rate C corresponds to the charging speed, i.e. the speed at which the electric battery 10 is charged. Preferably this charging rate is a function of the cycling protocol considered. During the development of the present invention, it was observed that the charging rate can have a significant impact on the behavior and degradation patterns of a LiB. Thus, it is observed that higher charging rates can accelerate the aging process and reduce the overall lifetime of the electric battery 10. The development work of the present invention has made it possible to obtain valuable information on the performance of the electric battery 10 under different charging conditions and thus to develop optimization strategies.

[0061] These five parameters have been identified as those having a significant effect on the state of degradation of an electric battery 10.

[0062] Next comes the processing step 140. This processing step uses the information relating to the initial cycling protocol, the data collected relating to the operating parameters of the electric battery 10 and the choice of the prediction cycling protocol. With these elements and a pre-trained mathematical model, the present invention makes it possible to generate at least one descriptor. This descriptor is then capable of classifying different degradation states of the electric battery 10 according to various variables and parameters. Advantageously, the descriptor classifies the degradation state of the battery 10 according to a set of predetermined classes, such as for example: a first class called “high loss”, a second class called “very high loss”, a third class called “low loss” and a fourth class called “moderate loss”. The first class can thus correspond to a high degradation rate.The second class may correspond to a very high degradation rate. The third class may correspond to a low degradation rate. The fourth class may correspond to a moderate degradation rate.

[0063] Advantageously, the present invention, by exploiting at least part of these parameters and preferably other so-called secondary parameters, makes it possible to generate a so-called pre-trained mathematical model. Indeed, by using data from manufacturers, integrators or even users, the development of the present invention has made it possible to design what is called artificial intelligence, that is to say a pre-trained mathematical model, making it possible to process data from parameters relating to an electric battery 10 in order to then design a mathematical model predictive of the state of degradation of said electric battery 10, preferably via a prediction of said state of degradation as a function of various variables.

[0064] It should be noted that a variable and a parameter can refer to the same data or physical quantity. However, we will speak of a parameter when it is a collected data and of a variable when it is a data intended to vary for the calculation of a prediction, for example.

[0065] Preferably, data collection has been an important step in building a predictive mathematical model based on machine learning during the development of the present invention. In this type of approach, the quality and quantity of the collected data have a direct impact on the accuracy and effectiveness of the predictive mathematical model thus generated. Preferably, the collected data includes a wide range of parameters to provide a comprehensive view of the performance of the electric battery 10 under different conditions, allowing the machine learning model to make accurate predictions, i.e. to generate a predictive mathematical model.

[0066] The parameters taken into consideration for the design of the pre-trained mathematical model include the parameters previously described and also additional or secondary parameters. These additional parameters are advantageously the following: a. A pressure P applied to at least a portion of the electric battery 10, said pressure preferably being predetermined and advantageously fixed. This parameter relates to the application of a pressure P to the electric battery 10 during cycling. This parameter provides a dimension of mechanical constraints, to the mathematical model during its design, relative to the performance of the electric battery 10 and its degradation under conditions of mechanical constraints; b. A discharge rate D relating to the cycling protocol of the electric battery 10: During the development of the present invention, different discharge rates were applied to evaluate their impact on the aging process of the electric battery 10 and its overall performance. It appears that the discharge rate D has a significant impact on the degradation of the performance of an electric battery. c. A charge limit L: This involves imposing a limit on the charge of an electric battery, such as 80% of its total charge capacity. It appears that using a charge limit L has a significant impact on the degradation of the performance of an electric battery. d. A rest time Tp at zero current: This involves imposing a stop time during the charging and / or discharging of an electric battery 10. During this rest time, the electric battery 10 has the opportunity to stabilize and recover from the stress imposed during the previous charge or discharge cycle. The duration of the rest period, i.e., the rest time, can influence the performance of the electric battery 10. It should be noted that rest times that are too short can lead to an increase in the stress on the electric battery 10, potentially accelerating the degradation mechanisms. Conversely, long rest times can allow for better relaxation of the chemical stresses, and thus improve the performance and longevity of the electric battery 10.

[0067] We will now present the variables that can be used for the prediction of the state of degradation of an electric battery 10 by the present invention. These variables include parameters that were at least partly used in the design of the pre-trained mathematical model. These so-called training parameters also include the parameters previously discussed. These training parameters become prediction variables when predicting the state of degradation of the electric battery 10. These prediction variables have the function of being used as adjustable variables, preferably by a user, when predicting the state of degradation of the electric battery 10. These variables are preferably the following: a. An initial state of charge of the electric battery 10; b. A final state of charge of the electric battery 10; c. A pressure P' applied to at least a portion of the electric battery 10, said pressure preferably being predetermined and advantageously fixed; d. A number N' of charge-discharge cycles of said electric battery 10 e. A temperature T' of the electric battery 10; f. A first charge rate Cl relative to the first cycling protocol; g. A second charge rate C2 relative to the second cycling protocol; h. A third C3 charge rate relative to the third cycling protocol; i. A first discharge rate DI relating to the first cycling protocol; j. A second discharge rate D2 relating to the second cycling protocol; k. A third discharge rate D3 relating to the third cycling protocol; 1. A load limit L'; m. A pause time Tp' at zero current; n. Another cycling protocol;

[0068] It should be noted that for the design of the pre-trained mathematical model, the variables / parameters considered were carefully controlled and varied within a predetermined range to ensure that the data were representative of real-life conditions. This data collection process involved running each protocol multiple times and collecting data at regular time intervals. This data was then stored in a database for processing and training at least one machine learning model.For this purpose, techniques well known to those skilled in the art (see for example the book: “An Introduction to Statistical Learning, Gareth James, Daniela Witten, Trevor Hastie, Robert Tibshirani, Springer New York, NY, 2013, 978-1-4614-7138-7”), such as k-means, or support vector machines, or SVM, were used to predict the degradation rate of the electric battery 10 as a function of the given parameters. Thus, this made it possible to design a pre-trained mathematical model serving as a basis for creating the predictive mathematical model according to the present invention. This predictive mathematical model is itself designed specifically for a considered electric battery 10 and not for a so-called “generic” electric battery as in the case of the pre-trained mathematical model.

[0069] The creation of a predictive mathematical model can be long and complex, which is why the present invention uses a pre-trained mathematical model as a starting point for developing a predictive mathematical model specific to an electric battery 10, this approach allows a considerable saving of time and system resources.

[0070] In developing the present invention, a data preprocessing step was very useful. Indeed, once the data was collected, it was preprocessed to adapt it to the machine learning algorithms. This includes cleaning the data, removing any irrelevant or redundant features and transforming the data into a digital format that can be fed into the machine learning models.

[0071] Then, the preprocessed data was divided into training and testing sets. The k-means technique was used to group similar data points, and then support vector machines SVM are trained on each group or cluster to predict the degradation rate of electric batteries 10 for a particular group of data.

[0072] As a reminder, unsupervised k-means analysis aims to identify k groups in the data set by optimizing the distances between each point and data with similarities and by maximizing cluster separations using predefined metrics known to the person skilled in the art.

[0073] The advantage of using multi-parameter classification is that it can handle data and capture the non-linear relationships between input parameters and the degradation state of the electric battery 10. It provides a flexible and adaptable framework for integrating different features and optimizing decision boundaries to accurately classify the degradation of the electric battery 10.

[0074] Once the support vector machine SVM is created, it can be used to predict the classification of new data points. In order to facilitate understanding and decision making for a user, a decision diagram 60 as illustrated in [Fig.4] can be created and makes it possible to illustrate the boundaries between the different classes in a dataset of the SVM model. The decision diagram 60 is a visual representation of the decision boundaries produced by the SVM classifier. According to one embodiment, the decision diagram 60 can be generated by the predictive mathematical model.

[0075] A decision graph can show the decision boundaries that the SVM has learned from the training data. Points on one side of the boundary are classified as belonging to one class, while points on the other side are classified as belonging to a different class. Advantageously and as described below, the visualization of this data can be done on different pairs of input parameters, i.e. as a function of various parameters such as those described previously. Therefore, the user can control the axis of the plots, i.e. choose the input variables that he wishes to visualize.

[0076] Thus, advantageously, the method according to the present invention can also comprise at least one step of displaying, by at least one display module 260 of said electronic system 200, at least one graphical representation 60 of said second mathematical model. This display step is for example very useful for representing the calculated degradation state to a user via a screen, for example. It is easy to imagine that the present invention equips an electric vehicle and that the driver can, via his dashboard, know when his battery 10 is at risk of breaking down and therefore know when maintenance of the battery 10 should be planned.

[0077] Preferably, the method according to the present invention may also comprise a step of interaction by a user with said predictive mathematical model via a user interface 260 of said electronic system 200. In this situation, the user could for example vary a variable of the prediction and thus see in real time the evolution of the state of degradation of the electric battery 10 in the time. For example, the user could charge his battery 10 according to the first cycling protocol, but when he makes this prediction, and he changes to the second cycling protocol, he could then realize that the second cycling protocol could be more advantageous for his battery 10 given the latter and its own parameters.

[0078] Thus, for example, the development of a graphical user interface (GUI) 260 is a step in the development of the present invention that has made it possible to make the second predictive mathematical model more accessible to a wider audience, including researchers, engineers and designers working on battery systems, and especially to the end user, for example the driver of an electric vehicle 10. The graphical interface 260 preferably provides an intuitive and user-friendly interface that allows the user to easily control the various input parameters that affect the aging process of the lithium-ion batteries 10, i.e. that affect the prediction.

[0079] This tool allows the user to enter his own cycling data and obtain a prediction of the degradation rate of his electric battery 10. The user can also view the predicted results in the form of decision graphs 60. This type of graph can include various areas 61, 62, 63 and 64 indicating different scenarios depending on input parameters. Thus, the present invention also allows for better decision-making. [Fig. 4] shows an example of implementation of such a graphical interface 260. In this figure the first class 61 is illustrated, as well as the second class 62, the third class 63 and the fourth class 64, as previously described.

[0080] According to an advantageous embodiment, the method may also comprise at least one step of retroactive control, via the BMS 40 for example, of at least one parameter of the battery 10. This embodiment is illustrated in [Fig.3]. In this figure, a retroactive control loop 50 is illustrated. Indeed, the electronic system 200 having generated the predictive mathematical model via the method 100, it is then possible for the BMS 40 to exploit this predictive mathematical model to adjust one or more parameters of the electric battery 10, preferably in real time, so as to optimize its performance.

[0081] It should be noted that according to one embodiment, the first step 110 of collecting said at least one piece of information relating to an initial cycling protocol may comprise a step of acquiring said information from at least one database 20 and / or from at least one set of sensors 30.

[0082] According to one embodiment, the electronic system is in communication, via a communication module 260, with a database 20 and / or a set of sensors 30. This set of sensors 30 is configured to allow the measurement of real-time preference of various parameters of an electric battery 10.

[0083] The present invention also relates to a computer program product comprising a plurality of instructions which when executed by at least one processor execute the method 100 according to the present invention.

[0084] The present invention also relates to a non-transitory memory medium comprising a computer program product according to the present invention.

[0085] We will now describe, through [Fig.2], an electronic system 200 according to an embodiment of the present invention. Preferably, this electronic system 200 comprises at least one processor and advantageously at least one non-transitory memory.

[0086] This electronic system 200 is preferably configured to execute the method 100. This electronic system 200 advantageously comprises at least: a. A communication module 260. This communication module 260 is preferably configured to communicate with at least one database 20 and / or at least one set of sensors 30; b. A first collection module 210. This first collection module 210 is advantageously configured to collect, preferably via the communication module 260, at least one item of information relating to the initial cycling protocol of an electric battery 10 in question; c. A selection module 220. This selection module 220 is preferably configured to select at least one prediction cycling protocol from a plurality of cycling protocols; d. A second collection module 230. This second collection module 230 may be identical to the first collection module 210 according to one embodiment. This second collection module 230 is advantageously configured to collect, preferably via the communication module 260, at least one piece of data relating to a set of parameters; e. A calculation module 240. This calculation module 240 advantageously comprises at least one pre-trained mathematical model. This calculation module 240 is advantageously configured to process by machine learning said information, said data and said prediction cycling protocol. This calculation module 240 is preferably configured to predict a state of degradation of said electric battery 10 by generating at least one predictive mathematical model configured to mathematically represent at least one evolution of the state of degradation of said electric battery 10.

[0087] It will be noted that a module may comprise one or more other modules.

[0088] According to one embodiment, the electronic system 200 may comprise a display module. This display module, as indicated above, can be configured to display at least one graphical representation of said predictive mathematical model. This graphical representation can be an aid to decision-making.

[0089] Preferably, the electronic system 200 may comprise a user interface 260. This user interface 260 may be configured to allow at least one interaction by a user with said predictive mathematical model. This allows him to select, for example, the parameters that he wishes to take into account in the prediction. This also allows him to vary the value(s) of certain variables to see the impact that this has on the prediction and therefore on the future degradation state of the electric battery 10.

[0090] Advantageously, the electronic system 200 may comprise a control module. This control module is preferably configured to retroactively control at least one parameter of said electric battery 10. According to one embodiment, this control module may be a BMS 40.

[0091] The present invention thus allows an improvement in the performance of an electric battery by anticipating its degradation rate via the generation of a predictive mathematical model allowing predictions.

[0092] The invention is not limited to the embodiments previously described and extends to all the embodiments covered by the claims.

[0093] All publications referred to in this specification are incorporated by reference in their entirety for all purposes of aiding in the understanding of the present invention.

[0094] Numerical references

[0095] 10 Electric battery

[0096] 20 Database

[0097] 30 Sensor assembly

[0098] 40 Electric Battery Management System BMS

[0099] 50 Feedback Loop

[0100] 60 Decision graph

[0101] 61 First class

[0102] 62 Second class

[0103] 63 Third class

[0104] 64 Fourth class

[0105] 100 Prediction method

[0106] 110 First collection stage

[0107] 120 Selection step

[0108] 130 Second collection stage

[0109]

[0110] [YES]

[0112]

[0113]

[0114]

[0115]

[0116]

[0117]

[0118]

[0119]

[0120] 140 Machine learning processing step 141 Calculation step 142 Classification step 143 Calculation step 144 Step of obtaining a predictive mathematical model 200 Electronic system 210 First collection module 220 Selection module 230 Second collection module 240 Calculation module 250 Communication module 260 Graphical user interface

Claims

1. Claims Method for predicting (100) the state of degradation of at least one electric battery (10), said method (100) being configured to be executed by at least one electronic system (200), said method (100) comprising at least: a. A first step of collecting (110) at least one piece of information relating to an initial cycling protocol, said initial cycling protocol being taken from at least the following plurality of cycling protocols: i. A first cycling protocol, said first cycling protocol being a constant current and constant voltage cycling protocol; ii. A second cycling protocol, said second cycling protocol being a pulsed current cycling protocol; iii. A third cycling protocol, said third cycling protocol being a multi-stage current cycling protocol; b. A step of selecting (120) at least one prediction cycling protocol taken from said plurality of cycling protocols; c. A second step of collecting (130) at least one piece of data relating to at least one set of parameters, said set of parameters comprising at least one of the following parameters: i. An initial state of charge of the electric battery; ii. A final state of charge of the electric battery; iii. A number N of charge-discharge cycles of said battery; iv. A temperature T of the electric battery; v. A charging rate C, i.e. a charging speed, associated with at least one cycling protocol taken from at least said plurality of cycling protocols; d. A processing step (140) by automatic learning from at least one pre-trained mathematical model, of said at least one piece of information, of said at least one data and the prediction cycling protocol, said processing step comprising at least: i. A step of calculating (141) at least one descriptor by applying said pre-trained mathematical model in a multidimensional calculation space, said multidimensional calculation space being configured so that each parameter of said set of parameters defines a dimension of said multidimensional calculation space; ii. A step of classifying (142) the state of degradation from said descriptor relative to a set of predetermined classes; iii. A step of calculating (143) the temporal evolution of said state of degradation of said electric battery (10), by calculating a plurality of states of degradation of said electric battery, as a function of at least one variable, said variable being taken from at least: • An initial state of charge of the electric battery (10); • A final state of charge of the electric battery (10); • Pressure applied to at least part of the electric battery (10); • A number N' of charge-discharge cycles of said electric battery (10); • A temperature T' of the electric battery (10); • A first charge rate Cl relative to the first cycling protocol; • A second C2 charge rate relating to the second cycling protocol; • A third C3 charge rate relating to the third cycling protocol; • A first DI discharge rate relative to the first cycling protocol; • A second discharge rate D2 relating to the second cycling protocol; • A third discharge rate D3 relating to the third cycling protocol; • A charge limit; • A pause time at zero current; • Another cycling protocol; iv. A step of obtaining (144) a calculated state of the degradation of said electric battery (10), said calculated state comprising at least one predictive mathematical model, said predictive mathematical model being configured to mathematically represent the evolution of the state of degradation of said electric battery (10) as a function of at least said variable.

2. Method (100) according to the preceding claim comprising at least one step of displaying, by at least one display module of said electronic system (200), at least one graphical representation (60) of said predictive mathematical model.

3. Method (100) according to any one of the preceding claims comprising at least one step of interaction by a user with said predictive mathematical model via a user interface (260) of said electronic system (200).

4. Method (100) according to any one of the preceding claims comprising at least one step of retroactive control, preferably by at least one management system (40) of the electric battery (10), of at least one variable as a function of said predictive mathematical model and / or at least one predetermined setpoint.

5. Method (100) according to the preceding claim in which the retroactive piloting step is carried out in real time.

6. Method (100) according to any one of the preceding claims wherein at least one of respectively the first collection step (110) and the second collection step (130) comprises the acquisition respectively of said information and said data from at least one database (20) and / or at least one set of sensors (30).

7. Computer program product, preferably recorded on a non-transitory memory medium, comprising instructions, which when performed by at least one of a processor, a computer, executes the method (100) according to any one of the preceding claims.

8. Non-transitory memory medium comprising said computer program product according to the preceding claim.

9. Electronic system (200) configured to execute the method (100) according to any one of claims 1 to 6, said electronic system (200) comprising at least: a. A communication module (250) configured to communicate with at least one database (20) and / or at least one set of sensors (30); b. A first collection module (210) configured to collect, preferably via the communication module (250), information relating to the initial cycling protocol of the electric battery (10); c. A selection module (220) configured to select at least one prediction cycling protocol from a plurality of cycling protocols; d. A second collection module (230) configured to collect, preferably via the communication module (250), data relating to a set of parameters; e. A computing module (240) configured to: i. Processing by machine learning from at least one pre-trained mathematical model, said at least one piece of information, said at least one piece of data and a prediction cycling protocol; ii. Compute at least one descriptor by applying said pre-trained mathematical model in a multidimensional computational space; iii. Classifying the state of degradation of said electric battery (10) from said descriptor relative to a set of predetermined classes; iv. Calculating the temporal evolution of said state of degradation of said electric battery (10), by calculating a plurality of states of degradation of said electric battery, as a function of at least one variable, said variable being taken from at least: • An initial state of charge of the electric battery (10); • A final state of charge of the electric battery (10); • Pressure applied to at least part of the electric battery (10); • A number N' of charge-discharge cycles of said electric battery (10); • A temperature T' of the electric battery (10); • A first charge rate Cl relative to the first cycling protocol; • A second C2 charge rate relating to the second cycling protocol; • A third C3 charge rate relating to the third cycling protocol; • A first DI discharge rate relative to the first cycling protocol; • A second discharge rate D2 relating to the second cycling protocol; • A third discharge rate D3 relating to the third cycling protocol; • A load limit; • A pause time at zero current; • Another cycling protocol; f. Generate at least one predictive mathematical model, said predictive mathematical model being configured to mathematically represent the evolution of the state of degradation of said electric battery (10) as a function of at least said variable.

10. System (200) according to the preceding claim comprising: a. at least one display module configured to display at least one graphical representation of said mathematical model, and b. at least one user interface (260) configured to allow at least one interaction by a user with said predictive mathematical model.

Images