# US 12,000,895 B2 · Method for predicting an aging state of a battery > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,000,895 B2 - Document ID: US12000895B2 - Status: Granted - Kind: B2 - Application number: 17/630,087 - Filed: 2020-10-29 - Published: 2022-08-11 - Granted: 2024-06-04 - Earliest claimed: 2019-11-08 - Assignees: Robert Bosch GmbH - Applicants: Robert Bosch GmbH - Inventors: Christian Simonis; Christoph Woll - Web page: https://patentgrep.com/patent/US12000895B2 ## CPC - G01R 31/367: Software therefor, e.g. for battery testing using modelling or look-up tables - H01M 10/48: Accumulators combined with arrangements for measuring, testing or indicating the condition of cells, e.g. the level or density of the electrolyte (constructional details of current conducting connections for detecting conditions inside cells or batteries, e.g. details of voltage sensing terminals, H01M50/569) - G01R 31/392: Determining battery ageing or deterioration, e.g. state of health - G07C 5/10: using counting means or digital clocks - H01M 10/42: Methods or arrangements for servicing or maintenance of secondary cells or secondary half-cells (H01M10/60 takes precedence) - H01M 2220/20: Batteries in motive systems, e.g. vehicle, ship, plane - G01R: MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES (indicating correct tuning of resonant circuits H03J3/12) - H01M: PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY - G07C: TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE ## Abstract A method for predicting an aging state of a battery. A vehicle is also provided that includes at least one battery, the aging state of which is predited using the method and/or the aging behavior of which is improved based on the aging state prediction. A prediction system that is configured to carry out the method is also provided. ## Claims ### Claim 1 A method for predicting an aging state of a battery, the method comprising: providing data of the battery as a function of various usage profiles of the battery; transmitting the data of the battery to a memory device in which data from multiple comparison batteries are stored, processed, and analyzed; determining aging state values of the battery at defined times and/or for defined events using a battery reference model; forming an aging state pattern of the battery based on the determined aging state values; and determining a predicted aging state value and/or a predicted aging state pattern of the battery: (i) by extrapolating the aging state pattern that is formed, and (ii) by associating the formed aging state pattern with an ascertained aging state pattern from the data of the comparison batteries stored in the memory device, multiple aging state patterns being ascertained from the data stored in the memory device. ### Claim 2 (depends on 1) The method as recited in claim 1, wherein the battery reference model is an artificial intelligence-based model. ### Claim 3 (depends on 1) The method as recited in claim 1, wherein the battery reference model is compared based on the data of the comparison batteries stored in the memory device. ### Claim 4 (depends on 1) The method as recited in claim 1, wherein the aging state values of the battery are determined for various prediction horizons. ### Claim 5 (depends on 1) The method as recited in claim 1, wherein the data of the battery are transmitted to the memory device using a wireless network. ### Claim 6 (depends on 1) The method as recited in claim 1, wherein the memory device is a cloud memory. ### Claim 7 (depends on 1) The method as recited in claim 1, wherein the data of the battery transmitted to the memory device are continuously monitored and assessed. ### Claim 8 (depends on 1) The method as recited in claim 1, wherein the data of the battery and of the comparison batteries stored in the memory device are continuously verified and assessed. ### Claim 9 (depends on 1) The method as recited in claim 1, wherein a load pattern is learned individually by a driver based on historical loads and utility patterns, and is then parameterized as a load prediction, including a current profile or a temperature profile. ### Claim 10 (depends on 9) The method as recited in claim 9, wherein the load prediction is input to the reference model to obtain a model-based SOH prediction, wherein the SOH prediction in the fusion module is merged with another SOH prediction from a data-driven fleet model. ### Claim 11 (depends on 10) The method as recited in claim 10, wherein there is a weighting of the two predictions, so as to provide a merged prediction. ### Claim 12 A vehicle, comprising: a device; and at least one battery, wherein an aging state of which is predicted and/or an aging behavior of which is improved based on the predicted aging state, wherein the aging state is predicted by the device; wherein the device is configured to perform the following: providing data of the battery as a function of various usage profiles of the battery; transmitting the data of the battery to a memory device in which data from multiple comparison batteries are stored, processed, and analyzed; determining aging state values of the battery at defined times and/or for defined events using a battery reference model; forming an aging state pattern of the battery based on the determined aging state values; and determining a predicted aging state value and/or a predicted aging state pattern of the battery: (i) by extrapolating the aging state pattern that is formed, and (ii) by associating the formed aging state pattern with an ascertained aging state pattern from the data of the comparison batteries stored in the memory device, multiple aging state patterns being ascertained from the data stored in the memory device. ### Claim 13 A prediction apparatus to predict an aging state of a battery, comprising: a prediction system configured to perform the following: providing data of the battery as a function of various usage profiles of the battery; transmitting the data of the battery to a memory device in which data from multiple comparison batteries are stored, processed, and analyzed; determining aging state values of the battery at defined times and/or for defined events using a battery reference model; forming an aging state pattern of the battery based on the determined aging state values; and determining a predicted aging state value and/or a predicted aging state pattern of the battery: (i) by extrapolating the aging state pattern that is formed, and (ii) by associating the formed aging state pattern with an ascertained aging state pattern from the data of the comparison batteries stored in the memory device, multiple aging state patterns being ascertained from the data stored in the memory device.