# US 2026/0147045 A1 · Removing spurious signal components in a measured motor current signal for optimized motor diagnosis

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

- Number: US 2026/0147045 A1
- Document ID: US20260147045A1
- Status: Published application
- Kind: A1
- Application number: 19/398,966
- Filed: 2025-11-24
- Published: 2026-05-28
- Earliest claimed: 2024-11-28
- Assignees: Siemens Aktiengesellschaft
- Applicants: Siemens Aktiengesellschaft
- Inventors: Timo Rieskamp; Thomas Decker; Christoph Ernst Ludwig; Vincent Malik
- Web page: https://patentgrep.com/patent/US20260147045A1

## CPC

- G01R 31/343: {in operation}
- H02P 6/34: Modelling or simulation for control purposes
- H02P 21/0025: {implementing a off line learning phase to determine and store useful data for on-line control}
- H02P 29/50: Reduction of harmonics
- G01R: MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES (indicating correct tuning of resonant circuits H03J3/12)
- H02P: CONTROL OR REGULATION OF ELECTRIC MOTORS, ELECTRIC GENERATORS OR DYNAMO-ELECTRIC CONVERTERS; CONTROLLING TRANSFORMERS, REACTORS OR CHOKE COILS

## Abstract

An assistance apparatus and computer-implemented method for removing spurious signal components in a measured motor current signal of an electric motor for optimized motor diagnosis is provided, including the steps: receiving the measured motor voltage signal and a measured motor current signal measured at the motor; generating a modelled current signal by a motor model depending on the measured motor voltage signal; generating a reference current signal by the motor model depending on an undisturbed sinusoidal motor voltage signal; adapting a noise removal module to infer optimal denoising parameters by inputting the modelled current signal and the reference current signal into the noise removal module; determining a denoised motor current signal by inputting the measured motor current signal into the adapted noise removal module; and outputting the denoised motor current signal for optimized motor diagnosis.

## Claims

### Claim 1

A computer-implemented method for removing spurious signal components in a measured motor current signal of an electric motor for optimized motor diagnosis, comprising:
receiving the measured motor voltage signal and a measured motor current signal measured at the motor;
generating a modelled current signal by a motor model depending on the measured motor voltage signal; and
generating a reference current signal by the motor model depending on an undisturbed sinusoidal motor voltage signal,
adapting a noise removal module to infer optimal denoising parameters by inputting the modelled current signal and the reference current signal into the noise removal module;
determining a denoised motor current signal by inputting the measured motor current signal into the configured noise removal module; and
outputting the denoised motor current signal for optimized motor diagnosis.

### Claim 2 (depends on 1)

The computer-implemented method according to claim 1, wherein inputting the denoised motor current signal to a motor current analyser which outputs a motor diagnosis result.

### Claim 3 (depends on 1)

The computer-implemented method according to claim 1, wherein the sinusoidal motor voltage signal is generated having a frequency equal to a frequency of a supplied motor voltage signal.

### Claim 4 (depends on 1)

The computer-implemented method according to claim 1, wherein the motor model is a deterministic simulation model, for example a high-fidelity finite elements model, a high-fidelity digital twin, or a trained data-based model or a combination of both simulating the motor.

### Claim 5 (depends on 2)

The computer-implemented method according to claim 2, wherein the motor current analyser is a motor current signature analyser (MCSA), or a machine learning model trained to analyse the motor current signal, the machine learning model selected from the group consisting of: a deep neural network, a self-organizing map or a decision tree.

### Claim 6 (depends on 1)

The computer-implemented method according to claim 1, wherein a set of denoising parameters are determined depending on a differential signal between the generated modelled current signal and the generated reference current signal by the noise removal module.

### Claim 7 (depends on 6)

The computer-implemented method according to claim 6, wherein the set of denoising parameters are determined by inputting a disparity between the modelled current signal and the reference current signal into a timeseries data filter, optimizing the timeseries data filter to minimize the disparity.

### Claim 8 (depends on 7)

The computer-implemented method according to claim 7, wherein the measured motor current is input to the trained timeseries data filter outputting the denoised motor current signal.

### Claim 9 (depends on 7)

The computer-implemented method according to claim 7, wherein the timeseries data filter is structured as a linear autoregressive model, a wiener filter, a kernel adaptive filter or a recurrent neural network.

### Claim 10 (depends on 1)

The computer-implemented method according to claim 1, wherein the noise removal module comprises a noise cancelling unit that filters out unwanted, spurious signal components of the measured motor current signal depending on a reference noise signal.

### Claim 11 (depends on 10)

The computer-implemented method according to claim 10, wherein the reference noise signal is generated by inputting the modelled current signal and the reference current signal into a noise extractor unit and estimating the reference noise signal caused by voltage fluctuations only.

### Claim 12 (depends on 11)

The computer-implemented method according to claim 11, wherein the reference noise signal is estimated by computing a difference between the simulated motor current and the reference current signal.

### Claim 13 (depends on 12)

The computer-implemented method according to claim 12, wherein the estimated reference noise signal is refined by filtering out frequency components which are commonly observed in measured motor signals, such as a fundamental supply frequency or winding harmonics.

### Claim 14

An assistance apparatus comprising at least one processor configured to perform the steps for an optimized motor diagnosis removing spurious signal components in a measured motor current signal of an electric motor comprising:
generating a modelled current signal by a motor model depending on the measured motor voltage signal; and
generating a reference current signal by the motor model depending on an undisturbed sinusoidal motor voltage signal,
adapting a noise removal module to infer optimal denoising parameters by inputting the modelled current signal and the reference current signal into the noise removal module;
determining a denoised motor current signal by inputting the measured motor current signal into the configured noise removal module; and
outputting the denoised motor current signal for optimized motor diagnosis.

### Claim 15 (depends on 1)

A computer program product, comprising a computer readable hardware storage device having computer readable program code stored therein, the program code executable by a processor of a computer system to implement a method claim 1 when the product is run on at least one digital computer.
