KR102638784B1 - Method and system for predicting remaining useful life of battery based on machine learning - Google Patents

Abstract

The present disclosure relates to a method for predicting remaining battery life based on machine learning, which is performed by at least one processor. The remaining battery life prediction method includes receiving battery data for predicting the remaining life of a target battery, modeling a characteristic curve for deterioration of the target battery based on the battery data, and using a machine learning model, and predicting the remaining lifespan of the target battery from the characteristic curve.

Description

Machine learning-based battery remaining life prediction method {METHOD AND SYSTEM FOR PREDICTING REMAINING USEFUL LIFE OF BATTERY BASED ON MACHINE LEARNING}

The present disclosure relates to a method and system for predicting the remaining life of a battery based on machine learning. Specifically, a method and system for predicting the remaining life of a target battery from a characteristic curve for deterioration of the target battery using a machine learning model. It's about.

Recently, as the penetration rate of electric vehicles has rapidly increased, the number of waste batteries used in electric vehicles is also expected to increase rapidly. Waste batteries maintain an efficiency of 70-80% even after reaching the end of their lifespan for use in automobiles. Since they are made of lithium ion and cause serious environmental pollution due to hazardous substances when disposed of, the need for reuse is emerging from the perspective of resource circulation. there is.

Meanwhile, the performance and remaining lifespan of waste batteries vary greatly depending on the user's usage pattern and environment, such as charge/discharge rate, temperature, and humidity, so it is necessary to diagnose the condition of the battery and predict its lifespan before reusing the battery. However, the existing diagnostic technology has a problem in that it is not effective as a method of diagnosing remaining lifespan through a simple test.

The present disclosure provides a machine learning-based method for predicting remaining battery life, a computer program stored in a recording medium, and a system (device) to solve the above problems.

The present disclosure may be implemented in various ways, including as a method, system (device), or computer program stored in a readable storage medium.

According to an embodiment of the present disclosure, a machine learning-based battery remaining life prediction method performed by at least one processor includes receiving battery data for predicting the remaining life of a target battery, based on the battery data, It includes modeling a characteristic curve for battery deterioration and predicting the remaining lifespan of the target battery from the characteristic curve using a machine learning model.

According to one embodiment of the present disclosure, the target battery includes a waste battery.

According to an embodiment of the present disclosure, the battery data includes at least one of a degree of deterioration of the target battery, basic information of the target battery, or capacity evaluation information of the target battery.

According to an embodiment of the present disclosure, the degree of deterioration of the target battery is obtained through disassembly and analysis of at least some cells of the target battery.

According to an embodiment of the present disclosure, capacity evaluation information of the target battery is obtained through charge/discharge evaluation of at least some cells of the target battery.

According to an embodiment of the present disclosure, the method further includes generating a status diagnosis result of the target battery based on the expected remaining lifespan of the target battery.

According to an embodiment of the present disclosure, the status diagnosis result of the target battery includes a status diagnosis grade of the target battery.

According to an embodiment of the present disclosure, the status diagnosis result of the target battery includes information recommending utilization of the target battery.

In order to execute the above-described method according to an embodiment of the present disclosure on a computer, a computer program stored in a computer-readable recording medium is provided.

An information processing system according to an embodiment of the present disclosure includes a communication module, a memory, and at least one processor connected to the memory and configured to execute at least one computer-readable program included in the memory, and at least one program Receives battery data for predicting the remaining lifespan of the target battery, models a characteristic curve for the deterioration of the target battery based on the battery data, and uses a machine learning model to estimate the remaining lifespan of the target battery from the characteristic curve. Contains instructions for prediction.

According to an embodiment of the present disclosure, by modeling a characteristic curve for deterioration of the target battery from battery data, the residual value of the target battery can be measured when the battery is reused even when there is no usage history data for the target battery.

According to an embodiment of the present disclosure, by modeling the past history of the battery through various modeling methods and predicting the remaining lifespan through a machine learning model, an objective indicator can be provided to an entity seeking to reuse the battery. In addition, by providing such objective indicators, demand for related technologies can be increased, including new businesses and government-level development measures.

According to an embodiment of the present disclosure, it is possible to contribute to more efficient resource distribution by subdividing suitable targets for battery reuse based on the expected lifespan of the battery obtained through a machine learning model.

The effects of the present disclosure are not limited to the effects mentioned above, and other effects not mentioned can be explained by those skilled in the art in the technical field to which this disclosure pertains from the description of the claims (hereinafter referred to as 'the person skilled in the art'). can be clearly understood.

Embodiments of the present disclosure will be described with reference to the accompanying drawings described below, in which like reference numerals indicate like elements, but are not limited thereto.
1 is a diagram illustrating an example of a method for predicting remaining battery life according to an embodiment of the present disclosure.
Figure 2 is a block diagram showing the internal configuration of an information processing system according to an embodiment of the present disclosure.
Figure 3 is a functional block diagram showing the internal configuration of a processor according to an embodiment of the present disclosure.
FIG. 4 is a diagram illustrating an example in which battery data is stored in a database according to an embodiment of the present disclosure.
Figure 5 is a diagram showing an example of a lifespan curve of a target battery according to an embodiment of the present disclosure.
Figure 6 is a diagram showing an example of a machine learning model according to an embodiment of the present disclosure.
FIG. 7 is a diagram illustrating an example in which a status diagnosis result of a target battery is provided on a user terminal according to an embodiment of the present disclosure.
Figure 8 is a flowchart showing a method for predicting remaining battery life based on machine learning according to an embodiment of the present disclosure.

Hereinafter, specific details for implementing the present disclosure will be described in detail with reference to the attached drawings. However, in the following description, detailed descriptions of well-known functions or configurations will be omitted if there is a risk of unnecessarily obscuring the gist of the present disclosure.

In the accompanying drawings, identical or corresponding components are given the same reference numerals. Additionally, in the description of the following embodiments, overlapping descriptions of identical or corresponding components may be omitted. However, even if descriptions of components are omitted, it is not intended that such components are not included in any embodiment.

Advantages and features of the disclosed embodiments and methods for achieving them will become clear by referring to the embodiments described below in conjunction with the accompanying drawings. However, the present disclosure is not limited to the embodiments disclosed below and may be implemented in various different forms. The present embodiments are merely provided to ensure that the present disclosure is complete and that the present disclosure does not convey the scope of the invention to those skilled in the art. It is provided only for complete information.

Terms used in this specification will be briefly described, and the disclosed embodiments will be described in detail. The terms used in this specification are general terms that are currently widely used as much as possible while considering the function in the present disclosure, but this may vary depending on the intention or precedent of a technician working in the related field, the emergence of new technology, etc. In addition, in certain cases, there are terms arbitrarily selected by the applicant, and in this case, the meaning will be described in detail in the description of the relevant invention. Accordingly, the terms used in this disclosure should be defined based on the meaning of the term and the overall content of the present disclosure, rather than simply the name of the term.

In this specification, singular expressions include plural expressions, unless the context clearly specifies the singular. Additionally, plural expressions include singular expressions, unless the context clearly specifies plural expressions. When it is said that a certain part includes a certain element throughout the specification, this does not mean excluding other elements, but may further include other elements, unless specifically stated to the contrary.

Additionally, the term 'module' or 'unit' used in the specification refers to a software or hardware component, and the 'module' or 'unit' performs certain roles. However, 'module' or 'unit' is not limited to software or hardware. A 'module' or 'unit' may be configured to reside on an addressable storage medium and may be configured to run on one or more processors. Thus, as an example, a 'module' or 'part' refers to components such as software components, object-oriented software components, class components and task components, processes, functions and properties. , procedures, subroutines, segments of program code, drivers, firmware, microcode, circuits, data, databases, data structures, tables, arrays, or variables. Components and 'modules' or 'parts' may be combined into smaller components and 'modules' or 'parts' or further components and 'modules' or 'parts'. Could be further separated.

According to an embodiment of the present disclosure, a 'module' or 'unit' may be implemented with a processor and memory. 'Processor' should be interpreted broadly to include general-purpose processors, central processing units (CPUs), microprocessors, digital signal processors (DSPs), controllers, microcontrollers, state machines, etc. In some contexts, 'processor' may refer to an application-specific integrated circuit (ASIC), programmable logic device (PLD), field programmable gate array (FPGA), etc. 'Processor' refers to a combination of processing devices, for example, a combination of a DSP and a microprocessor, a combination of a plurality of microprocessors, a combination of one or more microprocessors in combination with a DSP core, or any other such combination of configurations. You may. Additionally, 'memory' should be interpreted broadly to include any electronic component capable of storing electronic information. 'Memory' refers to random access memory (RAM), read-only memory (ROM), non-volatile random access memory (NVRAM), programmable read-only memory (PROM), erasable-programmable read-only memory (EPROM), May also refer to various types of processor-readable media, such as electrically erasable PROM (EEPROM), flash memory, magnetic or optical data storage, registers, etc. A memory is said to be in electronic communication with a processor if the processor can read information from and/or write information to the memory. The memory integrated into the processor is in electronic communication with the processor.

In this disclosure, 'machine learning model' may include any model used to infer an answer to a given input. According to one embodiment, the machine learning model may include an artificial neural network model including an input layer (layer), a plurality of hidden layers, and an output layer. Here, each layer may include multiple nodes. In this disclosure, a machine learning model may refer to an artificial neural network model, and an artificial neural network model may refer to a machine learning model.

In the present disclosure, 'waste battery' may refer to a battery that is subject to recycling or reuse as the State of Health (SoH), which indicates the lifespan of the battery, falls below a certain level due to continuous use. For example, in the case of electric vehicle batteries, if the SoH falls below 80%, they can be disposed of as waste batteries due to issues such as driving safety. Additionally, ‘waste batteries’ may be referred to as ‘used batteries’.

1 is a diagram illustrating an example of a method for predicting remaining battery life according to an embodiment of the present disclosure. According to one embodiment, a deterioration characteristic curve 130 of the target battery and a prediction result 150 of the remaining life of the target battery are generated from battery data 110 for predicting the remaining life of the target battery by the battery remaining life prediction method. You can.

According to one embodiment, battery data 110 may be input to the characteristic curve modeling unit 120 to predict the remaining lifespan of the target battery (118). In one embodiment, the battery data 110 may include at least one of a deterioration degree 112 of the target battery, basic information 114 of the target battery, or capacity evaluation information 116 of the target battery. The degree of deterioration 112 of the target battery may refer to the degree of change in performance of the battery. The degree of deterioration 112 of the target battery may be measured through disassembly and analysis of at least some cells of the target battery. The basic information 114 of the target battery may refer to information related to the specifications of the target battery. Basic information 114 of the target battery may be obtained during the warehousing process of the target battery. Additionally, the capacity evaluation information 116 of the target battery may refer to the current, voltage, capacity, etc. of the actual battery. Capacity evaluation information 116 of the target battery may be obtained through charge/discharge evaluation. Details about the battery data 110 will be described later with reference to FIG. 4 .

According to one embodiment, the deterioration characteristic curve 130 of the target battery may be modeled by the characteristic curve modeling unit 120 based on the received battery data 110. For example, the deterioration characteristic curve 130 of the target battery may be modeled using the degree of deterioration of the target battery, basic information of the target battery, and capacity evaluation information of the target battery as factors. The modeled degradation characteristic curve 130 can be used to estimate aging, deterioration, safety, etc. of the target battery.

According to one embodiment, the remaining lifespan prediction result 150 of the target battery may be calculated by the battery remaining lifespan prediction unit 140 from the deterioration characteristic curve 130 of the target battery. For example, the remaining lifespan prediction result 150 of the target battery may be calculated in the form of a remaining lifespan curve for at least a portion of the target battery. Additionally, a machine learning model may be used to calculate the remaining life prediction result 150 of the target battery.

Through the above-described configuration, the battery remaining life prediction method models the past history of the battery through various modeling methods and predicts the remaining life through a machine learning model, thereby providing objective indicators to entities seeking to reuse the battery. . In addition, the battery remaining life prediction method can increase demand for related technologies, such as new businesses and government-level development measures, by providing such objective indicators.

Figure 2 is a block diagram showing the internal configuration of the information processing system 200 according to an embodiment of the present disclosure. The information processing system 200 may include a memory 210, a processor 220, a communication module 230, and an input/output interface 240. As shown in FIG. 2, the information processing system 200 may be configured to communicate information and/or data over a network using a communication module 230. For example, the characteristic curve modeling unit 120 and the remaining battery life prediction unit 140 of FIG. 1 may be operated by the processor 220 of the information processing system 200.

Memory 210 may include any non-transitory computer-readable recording medium. According to one embodiment, the memory 210 is a non-permanent mass storage device such as random access memory (RAM), read only memory (ROM), disk drive, solid state drive (SSD), flash memory, etc. mass storage device). As another example, non-perishable mass storage devices such as ROM, SSD, flash memory, disk drive, etc. may be included in the information processing system 200 as a separate persistent storage device that is distinct from memory. Additionally, the memory 210 may store an operating system and at least one program code (e.g., code for characteristic curve modeling, prediction of remaining battery life, etc. installed and driven in the information processing system 200).

These software components may be loaded from a computer-readable recording medium separate from the memory 210. Recording media readable by such a separate computer may include recording media directly connectable to the information processing system 200, for example, floppy drives, disks, tapes, DVD/CD-ROM drives, memory cards, etc. It may include a recording medium that can be read by a computer. As another example, software components may be loaded into the memory 210 through the communication module 230 rather than a computer-readable recording medium. For example, at least one program may be a computer program (e.g., characteristic curve modeling, battery It may be loaded into the memory 210 based on a program for predicting remaining lifespan, diagnosing battery status, etc.).

The processor 220 may be configured to process instructions of a computer program by performing basic arithmetic, logic, and input/output operations. Commands may be provided to a user terminal (not shown) or another external system by the memory 210 or the communication module 230. For example, processor 220 may be configured to execute received instructions according to program code stored in a recording device such as memory 210.

The communication module 230 may provide a configuration or function for a user terminal (not shown) and the information processing system 200 to communicate with each other through a network, and a configuration for the information processing system 200 to communicate with an external system. Alternatively, a function may be provided. In one embodiment, control signals, commands, data, etc. provided under the control of the processor 220 of the information processing system 200 are transmitted to the user terminal and/or the communication module of the external system through the communication module 230 and the network. It may be transmitted to a user terminal and/or an external system. For example, the information processing system 200 may transmit remaining battery life, battery status, etc. to the user terminal and/or external system through the communication module 230 and the network. In another embodiment, the processor 220 of the information processing system 200 may receive control signals, commands, data, etc. from the user terminal and/or external system through the communication module 230 and the network. For example, the processor 220 of the information processing system 200 may receive battery data, etc. from the user terminal and/or an external system through the communication module 230 and a network.

In addition, the input/output interface 240 of the information processing system 200 is connected to the information processing system 200 or means for interfacing with a device (not shown) for input or output that the information processing system 200 may include. It can be. In FIG. 2 , the input/output interface 240 is shown as an element configured separately from the processor 220, but the present invention is not limited thereto, and the input/output interface 240 may be included in the processor 220. Information processing system 200 may include more components than those in FIG. 2 . However, there is no need to clearly show most prior art components.

The processor 220 of the information processing system 200 may be configured to manage, process, and/or store information and/or data received from a plurality of user terminals and/or a plurality of external systems. For example, the processor 220 may collect battery data for predicting the remaining lifespan of the target battery and model a characteristic curve for deterioration of the target battery based on the battery data. Additionally, the processor 220 may predict the remaining lifespan of the target battery from the characteristic curve using a machine learning model. Additionally, the processor 220 may generate a status diagnosis result of the target battery based on the expected remaining lifespan of the target battery.

FIG. 3 is a functional block diagram showing the internal configuration of the processor 220 according to an embodiment of the present disclosure. As shown, the processor 220 may include a characteristic curve modeling unit 310, a remaining battery life prediction unit 320, and a battery state diagnosis unit 330. In this case, the characteristic curve modeling unit 310 and the remaining battery life prediction unit 320 may correspond to the characteristic curve modeling unit 120 and the remaining battery life predicting unit 140 shown in FIG. 1 . In addition, programs related to the characteristic curve modeling unit 310, the remaining battery life prediction unit 320, and the battery status diagnosis unit 330 are stored or loaded in any storage medium (e.g., memory 210, etc.), and are stored in the processor. It can be accessed or executed by (220).

According to one embodiment, the characteristic curve modeling unit 310 may model a deterioration characteristic curve of a target battery based on received battery data. For example, the characteristic curve modeling unit 310 may model past data using the degree of deterioration of the target battery, basic information of the target battery, and capacity evaluation information of the target battery as factors.

According to one embodiment, the characteristic curve modeling unit 310 may utilize various methods as modeling methods for the deterioration characteristic curve. For example, a physical modeling method that describes in detail the physical and chemical reactions inside the battery, an experimental modeling method that matches the characteristics of the battery with experimental data using variables and special formulas, an electric circuit model, a stochastic model, etc. Methods such as using models and matching battery characteristics to experimental data based on physical laws can be used.

According to one embodiment, the remaining battery life prediction unit 320 may calculate a prediction result of the remaining lifespan of the target battery from the deterioration characteristic curve of the target battery. To this end, the remaining battery life prediction unit 320 may use a machine learning model. The machine learning model of the battery remaining life prediction unit 320 can use data related to the deterioration characteristic curve as input and the remaining life prediction result as output, and the input to output is many-to-output due to prediction of continuous time series data (N :N) can be learned and used as a model. For example, the machine learning model of the battery remaining life prediction unit 320 may include an artificial neural network (eg, RNN) model specialized for learning and predicting time series data. Details of the machine learning model structure of the battery remaining life prediction unit 320 will be described later with reference to FIG. 6.

According to one embodiment, the battery status diagnosis unit 330 may generate a status diagnosis result of the target battery based on the expected remaining lifespan of the target battery. For example, the battery status diagnosis unit 330 may evaluate the status diagnosis level of the target battery. In this case, the battery status diagnosis unit 330 can quantify the expected lifespan and safety of the target battery and determine the corresponding grade according to predetermined grade standards. As another example, the battery status diagnosis unit 330 may generate utilization recommendation information for the target battery. In this case, the battery status diagnosis unit 330 may provide information on utilization according to the status of the target battery.

According to one embodiment, the database 340 may collect and store various data for diagnosing battery status. Additionally, the database 340 can store and query the life expectancy results of the target battery and the status diagnosis results of the target battery. The processor 220 communicates with the database 340 and can exchange battery data for predicting the remaining life of the target battery, life prediction results, status diagnosis results, etc.

In FIG. 3, each component of the processor 220 represents functionally distinct functional elements, and a plurality of components may be implemented in an integrated manner in an actual physical environment. In addition, in FIG. 3, the processor 220 is implemented by dividing it into a characteristic curve modeling unit 310, a remaining battery life prediction unit 320, and a battery status diagnosis unit 330, but this is not limited to this, and some components are omitted or other components are implemented. Configurations may be added.

FIG. 4 is a diagram illustrating an example in which battery data 432, 452, and 462 are stored in the database 340 according to an embodiment of the present disclosure. According to one embodiment, battery data stored in the database 340 may include capacity evaluation information 432, battery deterioration degree 452, and cell basic information 462.

According to one embodiment, the target battery may be received for reuse and recycling diagnosis (410). In this case, the target battery may be a used battery (waste battery) and may be received in a state removed from the electric vehicle. Then, the battery pack of the target battery can be separated from the case (412). Additionally, the target battery pack may be divided into a plurality of modules, and each of the plurality of battery modules may be divided into a plurality of cells (414). Meanwhile, as the target battery is received, basic information about the target battery may be input into the battery storage system 460 (418). The battery storage system 460 is a type of computer system and can store basic information about the batteries received.

According to one embodiment, cell charge/discharge evaluation 420 may be performed on all or some cells of the target battery. Cell charge/discharge evaluation 420 may refer to a process of evaluating the capacity of a target battery cell through a repetitive charging and discharging process for at least some cells of the target battery. The electrical characteristics of the target battery cell can be measured through cell charge/discharge evaluation (420) (422). The evaluation data system 430 can automatically collect and load data generated through cell charge/discharge evaluation 420.

According to one embodiment, cell disassembly analysis 440 may be performed on all or some cells of the target battery. Cell disassembly analysis 440 may refer to the process of generating analysis data by disassembling and analyzing at least some cells of the target battery into four major materials, such as anode, cathode, separator, and electrolyte. Through the cell disassembly analysis (440), the crystal structure, surface shape, cross-sectional shape, side reactants, etc. of the materials of at least some cells of the target battery can be quantified and analyzed (442). Analysis data generated through cell disassembly analysis 440 may be loaded on the analysis data system 450.

According to one embodiment, the evaluation data system 430 may transmit the capacity evaluation information 432 of the loaded target battery to the database 340. Capacity evaluation information 432 of the target battery may include information on cells that can actually be used, such as current, voltage, and capacity of the target battery. Additionally, the analysis data system 450 may transmit the degree of deterioration 452 of the loaded target battery to the database 340. The degree of deterioration 452 of the target battery may include the degree of change measured through disassembly analysis of the target battery cell. Likewise, the battery storage system 460 may transmit basic cell information 462 of the target battery to the database 340. The cell basic information 462 of the target battery may include information related to the specifications of the battery, such as the manufacturer, manufacturing date, serial number, cell type, current, and voltage capacity of the target battery cell. The transmitted capacity evaluation information 432, deterioration degree 452, and cell basic information 462 of the target battery may be stored in the database 340 for each ID of the battery cell.

FIG. 5 is a diagram illustrating an example of a lifespan curve 500 of a target battery according to an embodiment of the present disclosure. According to one embodiment, the lifespan curve 500 of the target battery may be displayed including capacity evaluation information 510 of the target battery, a deterioration characteristic curve 520 of the target battery, and a remaining lifespan curve 530 of the target battery. there is. In this case, the capacity evaluation information 510 of the target battery may include the use period when the charge/discharge capacity of the target battery is 80%.

According to one embodiment, the deterioration characteristic curve 520 of the target battery may be modeled using capacity evaluation information of the target battery, degree of deterioration of the target battery, basic information of the target battery, etc. as factors. Since most of the data related to the usage history of the target battery does not exist, the deterioration characteristic curve 520 of the target battery is used in place of the usage history to accurately measure the residual value of the target battery, such as aging, deterioration, and stability. It can be.

According to one embodiment, the remaining lifespan curve 530 of the target battery may refer to a graph predicting the future lifespan curve of the target battery. In general, when the SoH of a battery is 80% or less, the remaining lifespan may be an important consideration in the reuse of the battery because it has the characteristic of rapidly deteriorating at a certain point. Therefore, a machine learning model can be used to predict the remaining lifespan of the target battery, and the machine learning model can output a remaining lifespan curve 530 of the target battery predicted from the deterioration characteristic curve 520 of the target battery.

Figure 6 is a diagram showing an example of a machine learning model according to an embodiment of the present disclosure. According to one embodiment, the artificial neural network model 600 may be used as a machine learning model. The artificial neural network model 600 is an example of a machine learning model, and in machine learning technology and cognitive science, it is a statistical learning algorithm implemented based on the structure of a biological neural network or a structure for executing the algorithm.

According to one embodiment, the artificial neural network model 600 has nodes, which are artificial neurons that form a network through the combination of synapses, as in a biological neural network, repeatedly adjusting the weights of synapses to determine the correct input corresponding to a specific input. By learning to reduce the error between the output and the inferred output, a machine learning model with problem-solving capabilities can be represented. For example, the artificial neural network model 600 may include a random probability model, a neural network model, etc. used in artificial intelligence learning methods such as machine learning and deep learning.

According to one embodiment, a machine learning model for predicting the remaining lifespan of a target battery from extracted features may be created in the form of an artificial neural network model 600. The artificial neural network model 600 is implemented as a multilayer perceptron (MLP) consisting of multiple layers of nodes and connections between them. The artificial neural network model 600 according to this embodiment can be implemented using one of various artificial neural network model structures including MLP. As shown in FIG. 6, the artificial neural network model 600 includes an input layer 620 that receives an input signal or data 610 from the outside, and an output layer that outputs an output signal or data 650 corresponding to the input data. (640), located between the input layer 620 and the output layer 640, receives a signal from the input layer 620, extracts the characteristics, and transmits it to the output layer 640. n (where n is a positive integer) It consists of hidden layers (630_1 to 630_n). Here, the output layer 640 receives signals from the hidden layers 630_1 to 630_n and outputs them to the outside.

The learning method of the artificial neural network model 600 includes a supervised learning method that learns to optimize problem solving by inputting a teacher signal (correct answer), and an unsupervised learning method that does not require a teacher signal. ) There is a way. According to one embodiment, a computing device (e.g., an information processing system, etc.) may determine each deterioration characteristic curve of a plurality of batteries, the remaining life and/or remaining life corresponding to each deterioration characteristic curve of the plurality of batteries, with respect to the machine learning model. The artificial neural network model 600 can be trained using learning data including the lifespan curve, that is, ground truth data, etc.

According to one embodiment, the input variable of the artificial neural network model 600 in the machine learning model may include a deterioration characteristic curve of the target battery. In this way, when the above-described input variables are input through the input layer 620, the output variables output from the output layer 640 of the artificial neural network model 600 are the remaining lifespan of the target battery (or the remaining lifespan curve of the target battery). It can be.

In this way, a plurality of input variables and a plurality of output variables corresponding to the input layer 620 and the output layer 640 of the artificial neural network model 600 are matched, respectively, and the input layer 620, the hidden layers 630_1 to 630_n, and By adjusting the synapse values between nodes included in the output layer 640, learning can be done so that the correct output corresponding to a specific input can be extracted. Through this learning process, the characteristics hidden in the input variables of the artificial neural network model 600 can be identified, and the nodes of the artificial neural network model 600 can be connected to reduce the error between the output variable calculated based on the input variable and the target output. You can adjust the synapse values (or weights) between them.

In one embodiment, the computing device receives the deterioration characteristic curve of the battery and performs machine learning to minimize the loss between the remaining lifespan of the battery, which is the ground truth, and the remaining lifespan of the battery output from the machine learning model. You can train a model. Using the artificial neural network model 600 learned in this way, the remaining lifespan of the target battery can be automatically generated from the machine learning model.

FIG. 7 is a diagram illustrating an example in which a status diagnosis result of a target battery is provided on the user terminal 720 according to an embodiment of the present disclosure. According to one embodiment, the user 710 receives a target battery including a status diagnosis grade 730 of the target battery, an expected remaining lifespan of the target battery 740, and utilization recommendation information 750 of the target battery through the user terminal 720. You can receive battery status diagnosis results.

According to one embodiment, as a result of diagnosing the condition of the target battery, the status diagnosis grade 730 of the target battery may be displayed on the user terminal 720. The status diagnosis grade 730 of the target battery may refer to a grade determined according to predetermined standards by quantifying the expected lifespan and safety of the target battery. For example, as shown in FIG. 7 , the status diagnosis grade 730 of the target battery may be displayed as one of the specified grades, and a numerical value of the status of the target battery may also be displayed.

According to one embodiment, the expected remaining life 740 of the target battery may be displayed on the user terminal 720 as a result of diagnosing the status of the target battery. For example, as shown in FIG. 7, the expected remaining lifespan 740 of the target battery may be displayed including the remaining lifespan curve of the target battery calculated using a machine learning model.

According to one embodiment, recommendation information 750 for utilization of the target battery may be displayed on the user terminal 720 as a result of diagnosing the status of the target battery. The utilization recommendation information 750 of the target battery may include information about a use depending on the state of the target battery. For example, if the target battery is a waste battery, the utilization recommendation information 750 may be displayed including the degree to which the target battery is suitable as a battery for other uses such as ESS, mobile charger, or mobile mobile device.

Figure 8 is a flowchart showing a machine learning-based remaining battery life prediction method 800 according to an embodiment of the present disclosure. Method 800 may be performed by at least one processor (e.g., processor 220) of an information processing system. As shown, the method 800 may begin by receiving battery data for predicting the remaining lifespan of a target battery (S810). In one embodiment, the target battery may include a waste battery.

In one embodiment, the battery data may include at least one of a degree of deterioration of the target battery, basic information of the target battery, or capacity evaluation information of the target battery. In one embodiment, the degree of deterioration of the target battery may be obtained through disassembly analysis of at least some cells of the target battery. Additionally, capacity evaluation information of the target battery may be obtained through charge/discharge evaluation of at least some cells of the target battery.

Then, the processor may model a characteristic curve for deterioration of the target battery based on the battery data (S820). Finally, the processor can predict the remaining lifespan of the target battery from the characteristic curve using a machine learning model (S830).

In one embodiment, the processor may generate a status diagnosis result of the target battery based on the expected remaining lifespan of the target battery. In one embodiment, the status diagnosis result of the target battery may include a status diagnosis grade of the target battery. In another embodiment, the status diagnosis result of the target battery may include a result of recommending utilization of the target battery.

The flowchart shown in FIG. 8 and the above description are only examples and may be implemented differently in some embodiments. For example, in some embodiments, the order of each step may be changed, some steps may be performed repeatedly, some steps may be omitted, or some steps may be added.

The above-described method may be provided as a computer program stored in a computer-readable recording medium for execution on a computer. The medium may continuously store a computer-executable program, or may temporarily store it for execution or download. In addition, the medium may be a variety of recording or storage means in the form of a single or several pieces of hardware combined. It is not limited to a medium directly connected to a computer system and may be distributed over a network. Examples of media include magnetic media such as hard disks, floppy disks and magnetic tapes, optical recording media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, And there may be something configured to store program instructions, including ROM, RAM, flash memory, etc. Additionally, examples of other media include recording or storage media managed by app stores that distribute applications, sites or servers that supply or distribute various other software, etc.

The methods, operations, or techniques of this disclosure may be implemented by various means. For example, these techniques may be implemented in hardware, firmware, software, or a combination thereof. Those skilled in the art will understand that the various illustrative logical blocks, modules, circuits, and algorithm steps described in connection with the disclosure herein may be implemented in electronic hardware, computer software, or combinations of both. To clearly illustrate this interchange of hardware and software, various illustrative components, blocks, modules, circuits, and steps have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the specific application and design requirements imposed on the overall system. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementations should not be interpreted as causing a departure from the scope of the present disclosure.

In a hardware implementation, the processing units used to perform the techniques may include one or more ASICs, DSPs, digital signal processing devices (DSPDs), programmable logic devices (PLDs). ), field programmable gate arrays (FPGAs), processors, controllers, microcontrollers, microprocessors, electronic devices, and other electronic units designed to perform the functions described in this disclosure. , a computer, or a combination thereof.

Accordingly, the various illustrative logical blocks, modules, and circuits described in connection with this disclosure may be general-purpose processors, DSPs, ASICs, FPGAs or other programmable logic devices, discrete gate or transistor logic, discrete hardware components, or It may be implemented or performed as any combination of those designed to perform the functions described in. A general-purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, such as a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in conjunction with a DSP core, or any other configuration.

For firmware and/or software implementations, techniques include random access memory (RAM), read-only memory (ROM), non-volatile random access memory (NVRAM), and PROM ( on computer-readable media such as programmable read-only memory (EPROM), electrically erasable PROM (EEPROM), flash memory, compact disc (CD), magnetic or optical data storage devices, etc. It can also be implemented with stored instructions. Instructions may be executable by one or more processors and may cause the processor(s) to perform certain aspects of the functionality described in this disclosure.

Although the above-described embodiments have been described as utilizing aspects of the presently disclosed subject matter in one or more standalone computer systems, the disclosure is not limited thereto and may also be implemented in conjunction with any computing environment, such as a network or distributed computing environment. . Furthermore, aspects of the subject matter of this disclosure may be implemented in multiple processing chips or devices, and storage may be similarly effected across the multiple devices. These devices may include PCs, network servers, and portable devices.

Although the present disclosure has been described in relation to some embodiments in this specification, various modifications and changes may be made without departing from the scope of the present disclosure as can be understood by a person skilled in the art to which the invention pertains. Additionally, such modifications and changes should be considered to fall within the scope of the claims appended hereto.

110: Battery data
112: Battery deterioration degree
114: Battery basic information
116: Capacity evaluation information
118: input
120: Characteristic curve modeling unit
130: Deterioration characteristic curve
140: Battery remaining life prediction unit
150: Remaining life prediction result

Claims (10)

In a machine learning-based battery remaining life prediction method performed by at least one processor,
Receiving battery data for predicting the remaining lifespan of a target battery, which is a waste battery;
modeling a characteristic curve for deterioration that is part of the lifespan curve of the target battery using the battery data as a factor; and
Predicting the remaining lifespan of the target battery from the characteristic curve using a machine learning model
Including,
The battery data is,
Contains a degree of deterioration of the target battery, basic information of the target battery, and capacity evaluation information of the target battery,
The degree of deterioration of the target battery is,
Obtained through disassembly analysis of at least some cells of the target battery,
The capacity evaluation information of the target battery is,
A method for predicting remaining battery life, obtained through charge/discharge evaluation of at least some cells of the target battery.
delete delete delete delete According to paragraph 1,
A method for predicting remaining battery life, further comprising generating a status diagnosis result of the target battery based on the expected remaining life of the target battery.
According to clause 6,
The status diagnosis result of the target battery is,
A method for predicting remaining battery life, including a status diagnosis grade of the target battery.
In paragraph 6,
The status diagnosis result of the target battery is,
A method for predicting remaining battery life, including recommended use information for the target battery.
A computer program stored in a computer-readable recording medium for executing the method according to any one of claims 1 and 6 to 8 on a computer.
As an information processing system,
communication module;
Memory; and
At least one processor connected to the memory and configured to execute at least one computer-readable program included in the memory,
The at least one program is,
Receive battery data to predict the remaining lifespan of the target battery, which is a waste battery,
Using the battery data as a factor, model a characteristic curve for deterioration that is part of the lifespan curve of the target battery,
Contains instructions for predicting the remaining lifespan of the target battery from the characteristic curve using a machine learning model,
The battery data is,
Contains a degree of deterioration of the target battery, basic information of the target battery, and capacity evaluation information of the target battery,
The degree of deterioration of the target battery is,
Obtained through disassembly analysis of at least some cells of the target battery,
The capacity evaluation information of the target battery is,
An information processing system obtained through charge/discharge evaluation of at least some cells of the target battery.

Images