US 11,938,838 B2
Method and device for the robust prediction of the aging behavior of an energy storage unit in a battery-operated machine
Christian Simonis, Leonberg (DE); and Christoph Woll, Gerlingen (DE)
Assigned to Robert Bosch GmbH, Stuttgart (DE)
Filed by Robert Bosch GmbH, Stuttgart (DE)
Filed on Sep. 28, 2021, as Appl. No. 17/487,895.
Claims priority of application No. 10 2020 212 297.0 (DE), filed on Sep. 29, 2020.
Prior Publication US 2022/0097561 A1, Mar. 31, 2022
Int. Cl. B60L 58/16 (2019.01); G01R 31/367 (2019.01); G01R 31/392 (2019.01); G06N 7/01 (2023.01); G06N 20/00 (2019.01); G07C 5/08 (2006.01)
CPC B60L 58/16 (2019.02) [G01R 31/367 (2019.01); G01R 31/392 (2019.01); G06N 7/01 (2023.01); G06N 20/00 (2019.01); G07C 5/0808 (2013.01)] 15 Claims
OG exemplary drawing
 
1. A method for determining a predicted state of health of an electrical energy storage unit in a machine, comprising:
providing a data-based or hybrid state of health model, the state of health model is trained, depending on operating variables of the electrical energy storage unit and/or operating features derived from the operating variables, to indicate a state of health and to indicate a model uncertainty of the indicated state of health;
ascertaining a state of health characteristic and an associated model uncertainty of the energy storage unit of the machine based on the operating variables using the state of health model with a data processing device operably connected to the machine and located remote from the machine;
defining characteristic of confidence intervals for the state of health of the energy storage unit of the machine;
generating at least one random constructed state of health characteristic candidate that corresponds to constructed state of health characteristics within the defined characteristic of confidence intervals using the data processing device;
checking the at least one random constructed state of health characteristic candidate for plausibility on a rule basis to identify each random constructed state of health characteristic as (i) at least one plausible state of health characteristic candidate, or (ii) at least one implausible state of health characteristic candidate,
selecting, from a plurality of provided real state of health characteristics of real energy storage units of other machines, a number of the real state of health characteristics that are closest to the at least one plausible random constructed state of health characteristic candidate using the data processing device;
ascertaining a probability density function of the selected number of real state of health characteristics in order to determine a characteristic of the average of the state of health as a predicted state of health characteristic using the data processing device;
signaling the predicted state of health characteristic; and
operating the machine based on the predicted state of health characteristic of the electrical energy storage unit,
wherein the rule basis includes identifying the at least one random constructed state of health characteristic candidate as being implausible when the at least one random constructed state of health characteristic candidate shows an increase in the state of health over an evaluation period, and
wherein the at least one implausible state of health characteristic candidate is not taken into consideration for ascertaining the probability density function.