# US 2021/0064969 A1 · Method for detecting a deterioration in a network

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

- Number: US 2021/0064969 A1
- Document ID: US20210064969A1
- Status: Published application
- Kind: A1
- Application number: 16/896,778
- Filed: 2020-06-09
- Published: 2021-03-04
- Earliest claimed: 2019-08-27
- Applicants: Robert Bosch GmbH
- Inventors: Christopher Huth; Marcel Kneib
- Web page: https://patentgrep.com/patent/US20210064969A1

## CPC

- G06N 3/047: Probabilistic or stochastic networks
- H04L 63/1425: {Traffic logging, e.g. anomaly detection}
- G06N 3/08: Learning methods
- G06N 3/092: Reinforcement learning
- G06N 20/00: Machine learning
- H04L 12/40: Bus networks
- H04L 63/14: {for detecting or protecting against malicious traffic}
- H04L 2012/40215: {Controller Area Network CAN}
- H04L 2012/40273: {the transportation system being a vehicle}
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

A method for detecting a deterioration of network components in a network. The method includes the evaluation, in an evaluation unit, of at least one ascertained signal parameter of a signal that is transmitted in a network, in order to determine a signal quality of the signal, and establishing that a deterioration of the network exists if the signal quality lies outside a predefined range.

## Claims

### Claim 1

A method for detecting a deterioration of network components in a network, the method comprising the following steps:
evaluating, in an evaluation unit, at least one ascertained signal parameter of a signal that is transmitted in a network to determine a signal quality of the signal; and
establishing that a deterioration of the network is present based on the signal quality lying outside a predefined range.

### Claim 2 (depends on 1)

The method as recited in claim 1, wherein the evaluation of the at least one signal parameter includes:
obtaining at least one modeled signal parameter from a mathematical network model which at least partly describes transmitted signals in the network;
comparing the at least one ascertained signal parameter with the at least one modeled signal parameter from the network model to determine the signal quality.

### Claim 3 (depends on 1)

The method as recited in claim 1, wherein the at least one ascertained signal parameter includes at least one of the following: (i) a clock pulse offset of the signal, (ii) a signal jitter, (iii) an edge steepness of a rising or falling signal edge, (iv) fluctuations in a signal voltage, (v) a frequency component of the signal, (vi) a bit length of a signal.

### Claim 4 (depends on 2)

The method as recited in claim 2, wherein the network model (200) includes at least one of the following: (i) a machine learning algorithm, (ii) a neural network, (iii) a stochastic model, (iv) a data-based model.

### Claim 5 (depends on 2)

The method as recited in claim 2, further comprising the following step:
adapting the network model based on the at least one ascertained signal parameter.

### Claim 6 (depends on 1)

The method as recited in claim 1, further comprising the following steps:
forming a signal quality value based on a plurality of ascertained signal parameters of a signal and/or based on a plurality of ascertained signal parameters of multiple signals from the same source; and
evaluating the signal quality value in order to determine the signal quality of the signal.

### Claim 7 (depends on 1)

The method as recited in claim 1, further comprising:
outputting a warning signal when a deterioration of the network is detected; and/or
ascertaining at least one signal parameter of the signal that is transmitted in the network.

### Claim 8 (depends on 2)

The method as recited in claim 2, further comprising the following step:
determining, based on the at least one signal parameter and the network model, from which transmitter in the network the signal originates from which the at least one evaluated signal parameter was ascertained.

### Claim 9 (depends on 1)

The method as recited in claim 1, further comprising:
evaluating the signal quality of signals from at least two different transmitters in the network.

### Claim 10 (depends on 1)

The method as recited in claim 1, further comprising the following step:
statistically evaluating the signal quality of signals in at least two different networks, wherein the networks have at least partly identical network characteristics.

### Claim 11 (depends on 10)

The method as recited in claim 10, further comprising the following step:
forming or adapting a prediction model for signals in a network of the networks based on its network characteristics.

### Claim 12 (depends on 1)

The method as recited in claim 1, wherein the network includes a Controller Area Network (CAN) bus in a vehicle.

### Claim 13

A processing unit configured to detect a deterioration of network components in a network, the processing unit configured to:
evaluate, in an evaluation unit, at least one ascertained signal parameter of a signal that is transmitted in a network to determine a signal quality of the signal; and
establish that a deterioration of the network is present based on the signal quality lying outside a predefined range.

### Claim 14

A non-transitory machine-readable memory medium on which is stored a computer program for detecting a deterioration of network components in a network, the computer program, when executed by a computer, causing the computer to perform:
evaluating, in an evaluation unit, at least one ascertained signal parameter of a signal that is transmitted in a network to determine a signal quality of the signal; and
establishing that a deterioration of the network is present based on the signal quality lying outside a predefined range.
