# US 12,183,897 B2 · Battery management apparatus, battery management method and battery pack > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,183,897 B2 - Document ID: US12183897B2 - Status: Granted - Kind: B2 - Application number: 17/612,497 - Filed: 2020-06-29 - Published: 2022-08-11 - Granted: 2024-12-31 - Earliest claimed: 2019-08-05 - Assignees: LG Energy Solution, Ltd. - Applicants: LG Energy Solution, Ltd. - Inventors: Bo-Mi Lim - Web page: https://patentgrep.com/patent/US12183897B2 ## CPC - H01M 10/425: {Structural combination with electronic components, e.g. electronic circuits integrated to the outside of the casing (printed circuits H05K1/00)} - H02J 7/80: including monitoring or indicating arrangements - G01R 31/3648: {comprising digital calculation means, e.g. for performing an algorithm} - G01R 31/367: Software therefor, e.g. for battery testing using modelling or look-up tables - H01M 10/482: {for several batteries or cells simultaneously or sequentially} - H01M 10/486: {for measuring temperature} - H02J 7/82: Control of state of charge [SOC] - G01R 31/392: Determining battery ageing or deterioration, e.g. state of health - H01M 2010/4271: {Battery management systems including electronic circuits, e.g. control of current or voltage to keep battery in healthy state, cell balancing} - H01M 2220/20: Batteries in motive systems, e.g. vehicle, ship, plane - H02J 7/663: {using battery or load disconnect circuits (H02J9/002 takes precedence)} - Y02E 60/10: Energy storage using batteries - H01M: PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY - H02J: ELECTRIC POWER NETWORKS; CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY - G01R: MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES (indicating correct tuning of resonant circuits H03J3/12) - Y02E: REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION ## Abstract There are provided a battery management apparatus, a battery management method and a battery pack. The battery management apparatus sets at least one of a plurality of external variables as a valid external variable for each internal variable using a plurality of input data sets associated with the external variables that can be observed outside a battery cell and a plurality of desired data sets associated with the internal variables that are not observed outside the battery cell. ## Claims ### Claim 1 A battery management apparatus, comprising: a memory unit configured to store first to mth input data sets, first to nth desired data sets, and first to nth reference values, each of m and n being a natural number of two or greater; and a control unit operably coupled to the memory unit, wherein the first to mth input data sets are associated with first to mth external variables that are observable outside the battery cell, respectively, wherein each of the first to mth input data sets includes a predetermined number of input values, wherein the first to nth desired data sets are associated with first to nth internal variables, respectively, wherein the first to nth internal variables rely on a chemical state inside the battery cell, and are not observable outside the battery cell, wherein each of the first to nth desired data sets includes the predetermined number of target values, and wherein the control unit is configured to set at least one of the first to mth external variables as a valid external variable for each of the first to nth internal variables, based on the first to mth input datasets, the first to nth desired data sets, and the first to nth reference values. ### Claim 2 (depends on 1) The battery management apparatus according to claim 1, wherein: the memory unit is further configured to store a main multilayer perceptron that defines a correspondence relationship between: the first to mth external variables; and the first to nth internal variables; and the control unit is further configured to: obtain first to nth output data sets from first to nth output nodes included in an output layer of the main multilayer perceptron by providing the first to mth input data sets to first to mth input nodes included in an input layer of the main multilayer perceptron, each of the first to nth output data sets including the predetermined number of result values; determine first to nth error factors, based on; the first to nth output data sets; and the first to nth desired data sets; and determine the first to nth reference values by comparing each of the first to nth error factors with a threshold error factor. ### Claim 3 (depends on 2) The battery management apparatus according to claim 2, wherein: the control unit is further configured to determine the jth error factor of the first to nth error factors to be equal to an error ratio of the jth output data set of the first to nth output data sets to the jth desired data set of the first to nth desired data sets; and j is a natural number of n or smaller. ### Claim 4 (depends on 3) The battery management apparatus according to claim 3, the control unit is further configured to set the jth reference value of the first to nth reference values to be equal to a first predetermined value when the jth error factor is smaller than the threshold error factor. ### Claim 5 (depends on 4) The battery management apparatus according to claim 4, wherein: the control unit is further configured to set the jth reference value to be equal to a second predetermined value when the jth error factor is equal to or greater than the threshold error factor; and wherein the second predetermined value is smaller than the first predetermined value. ### Claim 6 (depends on 1) The battery management apparatus according to claim 1, wherein: the control unit is further configured to: determine whether to set the ith external variable of the first to mth external variables as a valid external variable for the jth internal variable, based on the ith input data set of the first to mth input data sets, the jth desired data set of the first to nth desired data sets, and the jth reference value of the first to nth reference values, and learn a sub-multilayer perceptron associated with the jth internal variable using the ith input data set as training data when the ith external variable is set as the effective external variable for the jth internal variable; i is a natural number of m or smaller; and j is a natural number of n or smaller. ### Claim 7 (depends on 6) The battery management apparatus according to claim 6, wherein the control unit is further configured to: determine a multiple correlation coefficient between the ith input data set and the jth desired data set; and set the ith external variable as the valid external variable for the jth internal variable when an absolute value of the multiple correlation coefficient is greater than the jth reference value. ### Claim 8 (depends on 7) The battery management apparatus according to claim 7, wherein the control unit is further configured to exclude the ith external variable from the valid external variable for the jth internal variable when the absolute value of the multiple correlation coefficient is equal to or less than the jth reference value. ### Claim 9 (depends on 1) A battery pack comprising the battery management apparatus according to claim 1. ### Claim 10 A battery management method, comprising: storing first to mth input data sets, first to nth desired data sets, and first to nth reference values, each of m and n being a natural number of two or greater, the first to mth input data sets being associated with the first to mth external variables that are observable outside a battery cell, respectively, each of the first to mth input data sets including a predetermined number of input values, the first to nth desired data sets being associated with the first to nth internal variables that are not observable outside the battery cell, respectively, each of the first to nth desired data sets including the predetermined number of target values; and setting at least one of the first to m external variables as a valid external variable for each of the first to nth internal variables, based on the first to mth input data sets, the first to nth desired data sets, and the first to nth reference values. ### Claim 11 (depends on 10) The battery management method according to claim 10, wherein: the ith external variable of the first to mth external variables is set as the valid external variable for the jth internal variable of the first to nth internal variables when an absolute value of a multiple correlation coefficient between the ith input data set of the first to mth input data sets and the jth desired data set of the first to nth desired data sets is greater than the jth reference value of the first to nth reference values; i is a natural number of m or smaller; and j is a natural number of n or smaller.