Fault state detection apparatus

Inventors: Ralf Gitzel (Mannheim, DE); Stephan Wildermuth (Laudenbach, DE); Joerg Gebhardt (Mainz, DE); Joerg Ostrowski (Zürich, CH); Patrik Reto Kaufmann (Baden, CH)

Assignee: ABB Schweiz AG

G01N29/12 G01J5/10 G06T7/0004 G01J2005/0077 G01N2291/0289 G06T2207/10048 G06T2207/20081

View Patent ↗

Loading inventors, assignments & file history…

Monitor This Case

Get email alerts when status or documents change.

Order Certified Copies

Most orders are placed with the USPTO same day — all within 24 business hours.

Order via The Patent Place →

Pre-filled with this patent's details

Quick Facts

Patent No.: US 12704481
App. No.: 17/970,797
Granted: Aug 11, 2026
Kind: B2

External Links

USPTO Patent Center↗ Full Patent PDF↗

Abstract

A fault state detection apparatus includes an input unit and a processing unit. The input unit receives condition monitoring data. The processing unit implements a trained machine learning algorithm to analyze the received condition monitoring data to determine if the received condition monitoring data is associated with a fault state. The trained machine learning algorithm was trained on the basis of a plurality of non-fault state condition monitoring data and associated ground truth information and on the basis of a plurality of fault state condition monitoring data and associated ground truth information. A subset of the plurality of fault state condition monitoring data was generated from one or more non-fault state condition monitoring data. Generation of fault state conditioning monitoring data in the subset of the plurality of fault state condition monitoring data comprises a transformation of non-fault state condition monitoring data to fault state condition monitoring data.

Claims (27)

1 . A method for fault state detection, comprising:

by a sensor, obtaining a non-fault state infrared image, transmitting the non-fault state infrared image to a trained machine learning algorithm, and receiving the non-fault state infrared image by the trained machine learning algorithm;

receiving condition monitoring data comprising vibration data;

analyzing, by the trained machine learning algorithm, the received condition monitoring data to determine if the received condition monitoring data is associated with a fault state;

transforming non-fault state condition monitoring data to fault state condition monitoring data to generate the fault state condition monitoring data in a subset of a plurality of fault state condition monitoring data, wherein the transformation of the non-fault state condition monitoring data to the fault state condition monitoring data comprises adding a hot spot to the non-fault state infrared image, and wherein the hot spot is added at a random position within the non-fault state infrared image and alters the non-fault state infrared image,

wherein, the trained machine learning algorithm was trained on a basis of training data sets including a plurality of non-fault state condition monitoring data and associated ground truth information and on a basis of the plurality of fault state condition monitoring data and associated ground truth information and wherein the training data sets mitigated imbalances between training data reflecting healthy operations and training data representing faulty operations, wherein the plurality of non-fault state condition monitoring data comprises vibration data, the plurality of fault state condition monitoring data comprises vibration data, wherein the transformation of the non-fault state condition monitoring data to the fault state condition monitoring data further comprises increasing a vibration amplitude peak, wherein the non-fault state condition monitoring data are represented as a plurality of amplitudes in different frequency bins, wherein increasing the vibration amplitude peak comprises increasing an amplitude in one of the different frequency bins, and wherein the associated ground truth information of the plurality of fault state condition monitoring data includes a type of fault;

wherein, the subset of the plurality of fault state condition monitoring data was generated from one or more non-fault state condition monitoring data, and

determining the type of fault that led to a respective fault state data of the plurality of fault state condition monitoring data.

2 . The method according to claim 1 , wherein the received condition monitoring data comprises the vibration data and the plurality of non-fault state condition monitoring data comprises the vibration data and the plurality of fault state condition monitoring data comprises the vibration data, and wherein the transformation of the non-fault state condition monitoring data to fault state condition monitoring data comprises a decrease in the vibration amplitude peak.

3 . The method according to claim 2 , wherein the non-fault state condition monitoring data are represented as a plurality of amplitudes in the different frequency bins, and wherein the decrease in the vibration amplitude peak comprises a decrease in the amplitude in one of the different frequency bins.

4 . The method according to claim 1 , wherein the received condition monitoring data comprises the vibration data and the plurality of non-fault state condition monitoring data comprises the vibration data and the plurality of fault state condition monitoring data comprises the vibration data, and wherein the transformation of the non-fault state condition monitoring data to fault state condition monitoring data comprises a shift in the vibration amplitude peak.

5 . The method according to claim 4 , wherein the non-fault state condition monitoring data are represented as a plurality of amplitudes in the different frequency bins, and wherein the shift in the vibration amplitude peak comprises an increase in the amplitude in a first one of the different frequency bins and an associated decrease in the amplitude in a second one of the different frequency bins.

6 . The method according to claim 1 , wherein the transformation of the non-fault state condition monitoring data to the fault state condition monitoring data comprises a preservation of a total vibrational energy.

7 . The method according to claim 1 , wherein the transformation of the non-fault state condition monitoring data to the fault state condition monitoring data comprises a change of a total vibrational energy.

8 . The method according to claim 1 , wherein the received condition monitoring data comprises infrared image data and the plurality of non-fault state condition monitoring data comprises infrared image data and the plurality of fault state condition monitoring data comprises infrared image data, and wherein the transformation of the non-fault state condition monitoring data to the fault state condition monitoring data comprises the addition of the hot spot to the non-fault state infrared image.

9 . The method according to claim 1 , wherein the hot spot is added at a position within the non-fault state infrared image associated with a conductive part of an imaged object.

10 . The method according to claim 1 , wherein the received condition monitoring data comprises visible image data and the plurality of non-fault state condition monitoring data comprises visible image data and the plurality of fault state condition monitoring data comprises visible image data, and wherein the transformation of the non-fault state condition monitoring data to the fault state condition monitoring data comprises an addition of a scratch or dent to an object in a non-fault state visible image.

11 . A fault state detection apparatus, comprising:

an input unit and a processing unit executing the method according to claim 1 .

12 . A method of training a machine learning algorithm for a fault state detection apparatus, the method comprising:

providing a plurality of non-fault state condition monitoring data and associated ground truth information;

providing a plurality of fault state condition monitoring data and associated ground truth information, the providing comprising generating a subset of the plurality of fault state condition monitoring data from one or more non-fault state condition monitoring data, and wherein the generating of fault state conditioning monitoring data in the subset of the plurality of fault state condition monitoring data comprises transforming non-fault state condition monitoring data to fault state condition monitoring data, wherein the transformation of the non-fault state condition monitoring data to the fault state condition monitoring data comprises adding a hot spot to a non-fault state infrared image, and wherein the hot spot is added at a random position within the non-fault state infrared image and alters the non-fault state infrared image;

implementing a machine learning algorithm;

training the machine learning algorithm on a basis of training data sets including the plurality of non-fault state condition monitoring data and the associated ground truth information and the plurality of fault state condition monitoring data and the associated ground truth information, wherein the training data sets mitigate imbalances between training data reflecting healthy operations and training data representing faulty operations;

receiving condition monitoring data comprising vibration data;

analyzing, by the trained machine learning algorithm, the received condition monitoring data to determine if the received condition monitoring data is associated with a fault state, wherein the plurality of non-fault state condition monitoring data comprises vibration data, the plurality of fault state condition monitoring data comprises vibration data, wherein the transformation of the non-fault state condition monitoring data to the fault state condition monitoring data further comprises increasing a vibration amplitude peak, wherein the non-fault state condition monitoring data are represented as a plurality of amplitudes in different frequency bins, wherein increasing the vibration amplitude peak comprises increasing an amplitude in one of the different frequency bins, and wherein the associated ground truth information of the plurality of fault state condition monitoring data includes a type of fault; and

determining the type of fault that led to a respective fault state data of the plurality of fault state condition monitoring data.