# US 2026/0036974 A1 · Method of training a machine learning model for detecting one or more faults

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

- Number: US 2026/0036974 A1
- Document ID: US20260036974A1
- Status: Published application
- Kind: A1
- Application number: 18/998,923
- Filed: 2023-07-14
- Published: 2026-02-05
- Earliest claimed: 2022-07-27
- Assignees: Siemens Aktiengesellschaft
- Applicants: Siemens Aktiengesellschaft
- Inventors: Vincent Malik; Mohamed Khalil; Christian Andreas Wolf Pozzo; Ali Al Hage Ali
- Web page: https://patentgrep.com/patent/US20260036974A1

## CPC

- G05B 23/024: {Quantitative history assessment, e.g. mathematical relationships between available data; Functions therefor; Principal component analysis [PCA]; Partial least square [PLS]; Statistical classifiers, e.g. Bayesian networks, linear regression or correlation analysis; Neural networks}
- G06F 30/27: using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
- G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

A method of training a machine learning model for detecting one or more faults associated with at least one component of a drive train includes providing a simulation model associated with the at least one component. The method includes configuring the simulation model using a predefined configuration for generating training data for the machine learning model, generating the training data using the configured simulation model, and training the machine learning model using the generated training data for detecting the health of at least one component of the drive train. The simulation model is configured to simulate a plurality of conditions based on the predefined configuration, for generating training data that includes a plurality of datasets. At least one dataset from the plurality of datasets is associated with a corresponding fault of the at least one component of the drive train.

## Claims

### Claim 1

A method of training a machine learning model for detecting one or more faults associated with at least one component of a drive train, the method comprising:
a. providing a simulation model associated with the at least one component of the drive train, the simulation model for simulating an operation of at least one component of the drive train;
b. configuring the simulation model using a predefined configuration, for generating training data for the machine learning model, wherein the simulation model is configured to simulate a plurality of conditions based on the predefined configuration,
c. generating the training data using the configured simulation model, wherein the training data comprises a plurality of datasets, wherein at least one dataset from the plurality of datasets is associated with a corresponding fault of the at least one component of the drive train;
d. training the machine learning model using the generated training data for detecting the health of at least one component of the drive train;
wherein the trained machine learning model is configured to receive sensor data associated with the at least one component of the drive train and detect the one or more faults associated the at least one component of the drive train based on the received sensor data.

### Claim 2 (depends on 1)

The method as claimed in claim 1, wherein the predefined configuration includes a plurality of parameters associated with the at least one component of the drive train, each parameter further comprising a plurality of values associated with the corresponding parameter.

### Claim 3 (depends on 1)

The method as claimed in claim 1, wherein the plurality of datasets includes at least another dataset, wherein the at least another dataset is associated with a normal operation of the at least one component of the drive train.

### Claim 4 (depends on 1)

The method as claimed in claim 1, wherein the sensor data includes vibration data associated with the at least one component of the drive train.

### Claim 5 (depends on 1)

The method as claimed in claim 1, wherein the drive train includes a motor connected to a load using a gear box.

### Claim 6 (depends on 2)

The method as claimed in claim 2, wherein the plurality of parameters includes a first set of parameters is associated with one or more faults associated with the at least one component of the drive train and a second set of parameters associated with operation of the at least one component of the drive train.

### Claim 7

A computing device for training a machine learning model for detecting one or more faults associated with at least one component of a drive train, the computing device comprising:
a. One or more processors connected to a memory module, the one or more processors configured to:
i. configure the simulation model using a predefined configuration, for generating training data for the machine learning model, wherein the simulation model is configured to simulate operation of at least one component of the drive train in a plurality of conditions based on the predefined configuration,
ii. generate the training data using the configured simulation model, wherein the training data comprises a plurality of datasets, wherein at least one dataset from the plurality of datasets is associated with a corresponding fault of the at least one component of the drive train;
iii. train the machine learning model using the generated training data for detecting the health of at least one component of the drive train;
wherein the trained machine learning model is configured to receive sensor data associated with the at least one component of the drive train and detect the one or more faults associated the at least one component of the drive train based on the received sensor data.

### Claim 8

A non transitory storage medium containing a plurality of instructions, which when executed on one or more processors, cause the one or more processors to:
a. configure the simulation model using a predefined configuration, for generating training data for the machine learning model, wherein the simulation model is configured to simulate operation of at least one component of the drive train in a plurality of conditions based on the predefined configuration,
b. generate the training data using the configured simulation model, wherein the training data comprises a plurality of datasets, wherein at least one dataset from the plurality of datasets is associated with a corresponding fault of the at least one component of the drive train;
c. train the machine learning model using the generated training data for detecting the health of at least one component of the drive train;
wherein the trained machine learning model is configured to receive sensor data associated with the at least one component of the drive train and detect the one or more faults associated the at least one component of the drive train based on the received sensor data.
