# US 2025/0096289 A1 · Fuel cell system and method for operating a fuel cell system

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2025/0096289 A1
- Document ID: US20250096289A1
- Status: Published application
- Kind: A1
- Application number: 18/728,918
- Filed: 2023-01-12
- Published: 2025-03-20
- Earliest claimed: 2022-01-18
- Assignees: Robert Bosch GmbH
- Applicants: Robert Bosch GmbH
- Inventors: Simon Buehler; Timo Bosch; Tobias Falkenau; Christopher Bruns
- Web page: https://patentgrep.com/patent/US20250096289A1

## CPC

- H01M 8/04447: {of anode reactants at the inlet or inside the fuel cell}
- H01M 8/04097: {with recycling of the reactants (H01M8/04119, H01M8/04104 take precedence)}
- H01M 8/04776: {at auxiliary devices, e.g. reformer, compressor, burner}
- H01M 8/04992: characterised by the implementation of mathematical or computational algorithms, e.g. feedback control loops, fuzzy logic, neural networks or artificial intelligence
- Y02E 60/50: Fuel cells
- H01M: PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- Y02E: REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION

## Abstract

The invention relates to a method (100) for operating a fuel cell system (200), the method (100) comprising: a first determination step (101), in which a hydrogen concentration supplied to a fuel cell stack (203) of the fuel cell system (200) by means of an inlet valve (209) of the fuel cell system (200) is determined, a second determination step (103), in which a nitrogen volume flow flowing through the fuel cell stack (203) is determined, and an adjustment step (105), in which a rotational speed of a recirculation fan (205) of the fuel cell system (200) is adjusted on the basis of the determined hydrogen concentration and the determined nitrogen volume flow. The invention also relates to a fuel cell system (200) and a to computer program product according to the appended claims.

## Claims

### Claim 1

A method (100) for operating a fuel cell system (200), wherein the method (100) comprises:
determining a hydrogen concentration supplied to a fuel cell stack (203) of the fuel cell system (200) by means of an inlet valve (209) of the fuel cell system (200),
determining a nitrogen volume flow flowing through the fuel cell stack (203), and
adjusting a rotational speed of a recirculation fan (205) of the fuel cell system (200) based on the determined hydrogen concentration and the determined nitrogen volume flow.

### Claim 2 (depends on 1)

The method (100) according to claim 1, wherein
a lambda value of the fuel cell system (200) is determined based on the determined hydrogen concentration and the determined nitrogen volume flow, and the rotational speed of the recirculation fan (205) is adjusted on the basis of the lambda value.

### Claim 3 (depends on 1)

The method (100) according to claim 1, wherein:
the rotational speed of the recirculation fan (205) is adjusted such that a specified lambda value is adjusted in the fuel cell system (200).

### Claim 4 (depends on 1)

The method (100) according to claim 1, wherein,
the nitrogen volume flow is determined based on a difference between a pressure in the flow direction of the nitrogen volume flow upstream of the fuel cell stack (203) and a pressure in the flow direction flow of the nitrogen volume flow downstream of the fuel cell stack (203).

### Claim 5 (depends on 1)

The method (100) according to claim 1, wherein
the hydrogen concentration is determined via a machine learner without a physical hydrogen concentration sensor.

### Claim 6 (depends on 5)

The method (100) according to claim 5, wherein
the machine learner is trained in a training fuel cell system comprising a hydrogen concentration sensor and is validated based on the hydrogen concentration values determined by the hydrogen concentration sensor,
wherein the machine learner receives as input signals an operating parameter of a recirculation fan (205) of the training fuel cell system and a parameter for an electrical state of the fuel cell stack (203) of the training fuel cell system.

### Claim 7 (depends on 5)

The method (100) according to claim 5, wherein
the machine learner comprises a data model.

### Claim 8

A fuel cell system (200) comprising an electronic controller (201),
wherein the electronic controller (201) is configured to:
determine a hydrogen concentration supplied to a fuel cell stack (203) of the fuel cell system (200) by means of an inlet valve (209) of the fuel cell system (200), determine a nitrogen volume flow flowing through the fuel cell stack (203), and adjust a rotational speed of a recirculation fan (205) of the fuel cell system (200) on the basis of the determined hydrogen concentration and the determined nitrogen volume flow.

### Claim 9

A non-transitory, computer-readable medium containing instructions which, when executed on a computer, configures the computer to determine a hydrogen concentration supplied to a fuel cell stack (203) of the fuel cell system (200) by means of an inlet valve (209) of the fuel cell system (200), determine a nitrogen volume flow flowing through the fuel cell stack (203), and adjust a rotational speed of a recirculation fan (205) of the fuel cell system (200) on the basis of the determined hydrogen concentration and the determined nitrogen volume flow.
