IP Library › Granted Patent US 12,436,194
Granted Patent B2
US 12,436,194 · App. 17/754,840 · Granted Oct 7, 2025

Fault detection in synchronous machines

Inventors: Hossein Ehya (Trondheim, NO); Arne Nysveen (Trondheim, NO)
Assignee: NORWEGIAN UNIVERSITY OF SCIENCE AND TECHNOLOGY (NTNU)
G01R31/34
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 12,436,194
App. No.
17/754,840
Granted
Oct 7, 2025
Kind
B2
Abstract

A method of fault detection in synchronous machines includes using at least one sensor to determine parameters linked to the magnetic field generated within the synchronous machine including parameters based on one or more of magnetic field strength, rotor current or voltage, stator current or voltage, and vibration. The sensor measurements are processed to identify data artefacts linked to the magnetic field, wherein the processing includes one or more signal processing techniques based on time, frequency, and both time and frequency. Subsequently, the output of the signal processing is analysed in order to identify and categorise irregularities in the magnetic field that are indicative of a fault in the synchronous machine. The analysing step includes recognising patterns in the processed sensor measurements, via use of computer aided pattern recognition techniques such as via machine learning algorithms.

Claims (36)

1. A method of fault detection in synchronous machines, wherein the method is carried out during start-up or shut-down of a synchronous machine, during which there is a transient magnetic field; the method comprising:

using at least one sensor to determine sensor measurements of one or more of magnetic field strength, rotor current or voltage, stator current or voltage, and vibration;

processing the sensor measurements to identify data artefacts linked to the transient magnetic field, wherein the processing includes one or more signal processing techniques based on any of time, frequency, and both time and frequency; and

analysing an output of the processing in order to identify and categorise irregularities in the transient magnetic field that are indicative of a fault in the synchronous machine, wherein the analysing includes using computer aided pattern recognition to recognise patterns in the processed sensor measurements.

2. A method as claimed in claim 1 , wherein the irregularities in the transient magnetic field are indicative of faults linked with one or more of eccentricity faults, damper winding faults, and short circuit faults.

3. A method as claimed in claim 1 , wherein the synchronous machine is a hydropower generator.

4. A method as claimed in claim 1 , wherein the at least one sensor includes at least one existing sensor configured to control the synchronous machine during operation of the synchronous machine.

5. A method as claimed in claim 1 , wherein the using at least one sensor to determine sensor measurements comprises using one or more existing sensors comprising one or more voltage or current sensors configured for use to monitor and/or control the synchronous machine during operation of the synchronous machine.

6. A method as claimed in claim 1 , wherein the sensor measurements do not include any data from a sensor on a moving part of a rotor of the machine.

7. A method as claimed in claim 1 , wherein the using at least one sensor to determine sensor measurements comprises using a sensor provided for the synchronous machine at a potential transformer thereof.

8. A method as claimed in claim 1 , wherein the processing the sensor measurements includes determining a radius of gyration for the rotor of the synchronous machine and the analysing the output of the signal processing includes recognising characteristic patterns in the radius of gyration to identify and categorise irregularities in the transient magnetic field.

9. A method as claimed in claim 8 , wherein the determining the radius of gyration data includes performing time series data mining on the sensor measurements, and the recognising characteristic patterns in the radius of gyration data is to detect a damper winding fault or an eccentricity fault.

10. A method as claimed in claim 8 , wherein the sensor measurements include measurements of the induced voltage in the field winding of the synchronous machine, and the determining the radius of gyration date includes mapping the phase space for the induced voltage in the field winding of the synchronous machine.

11. A method as claimed in claim 10 , wherein the using at least one sensor to determine sensor measurements includes using a sensor at a potential transformer to determine measurements of the induced voltage.

12. A method as claimed in claim 8 , wherein the analysing the output of the signal processing is to identify a damper winding fault in the form of a broken damper bar, and wherein the analysing the output of the signal processing includes a comparison of the measured radius of gyration compared to equivalent measurements of radius of gyration for a healthy synchronous machine.

13. A method as claimed in claim 8 , including wherein the analysing the output of the signal processing is to identify an eccentricity fault, and wherein the analysing the output of the signal processing includes determining a normalised radius of gyration with reference to a radius of gyration for a machine that is known to be healthy, with the normalised radius of gyration being defined as the difference between a radius of gyration for a healthy synchronous machine and the measured radius of gyration, with this difference being divided by the healthy radius of gyration.

14. A method as claimed in claim 13 , wherein the analysing the output of the signal processing includes automated identification and categorisation of possible eccentricity faults by assessing the value of the normalised radius of gyration compared to a threshold value.

15. A method as claimed in claim 1 , wherein the computer aided pattern recognition is based on a machine learning algorithm trained with a plurality of sensor measurements that have been signal processed to identify data artefacts linked to the transient magnetic field and that are known to relate to fault free machines as well as a plurality of sensor measurements that have been signal processed to identify data artefacts linked to the transient magnetic field and that are known to relate to machines with a fault.

16. A method as claimed in claim 1 , wherein the at least one sensor includes at least one non-invasive sensor mounted external to the machine and/or configured to take measurements in a contactless fashion.

17. A fault detection system for fault detection in synchronous machines, the fault detection system comprising:

a data processing apparatus for connection to at least one sensor in order to receive sensor measurements of one or more of magnetic field strength, rotor current or voltage, stator current or voltage, and vibration during start-up or shut-down of a synchronous machine, during which there is a transient magnetic field;

wherein the data processing apparatus is configured to:

process the sensor measurements determined during start-up or shut-down of the machine to identify data artefacts linked to the transient magnetic field, wherein the processing includes one or more signal processing techniques based on any of time, frequency, and both time and frequency; and

analyse an output of the processing in order to identify and categorise irregularities in the transient magnetic field that are indicative of a fault in the synchronous machine, wherein the analysing includes recognising patterns in the processed sensor measurements using computer aided pattern recognition.

18. A fault detection system as claimed in claim 17 , wherein the data processing apparatus is configured to:

use the at least one sensor to determine sensor measurements of one or more of magnetic field strength, rotor current or voltage, stator current or voltage, and vibration, during start-up or shut-down of the machine, during which there is a transient magnetic field.

19. A fault detection system as claimed in claim 17 , comprising at least one existing sensor configured to control the synchronous machine during operation of the synchronous machine and/or at least one non-invasive sensor mounted external to the machine and/or configured to take measurements in a contactless fashion.

20. A fault detection system as claimed in claim 17 , wherein the fault detection system does not use sensors placed on moving parts of a rotor of the machine.

21. A large synchronous machine acting as a hydropower generator, the synchronous machine including the fault detection system of claim 17 .

22. A non-transitory computer-readable medium comprising instructions that, when executed within a fault detection system as in claim 17 , will configure the data processing apparatus thereof to:

process the sensor measurements determined during start-up or shut-down of the machine to identify data artefacts linked to the transient magnetic field, wherein the processing includes one or more signal processing techniques based on any of time, frequency, and both time and frequency; and

analyse the output of the signal processing in order to identify and categorise irregularities in the transient magnetic field that are indicative of a fault in the synchronous machine, wherein the analysing includes recognising patterns in the processed sensor measurements using computer aided pattern recognition techniques.

23. A non-transitory computer-readable medium as claimed in claim 22 , comprising instructions arranged to configure the data processing apparatus to perform a method of:

using the at least one sensor to determine sensor measurements of one or more of magnetic field strength, rotor current or voltage, stator current or voltage, and vibration, during start-up or shut-down of the machine, during which there is a transient magnetic field;

processing the sensor measurements determined during start-up or shut-down of the machine to identify data artefacts linked to the transient magnetic field, wherein the processing includes one or more signal processing techniques based on any of time, frequency, and both time and frequency; and

analysing the output of the signal processing in order to identify and categorise irregularities in the transient magnetic field that are indicative of a fault in the synchronous machine, wherein the analysing includes recognising patterns in the processed sensor measurements using computer aided pattern recognition techniques.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 28, 2022
From: EHYA, HOSSEIN; NYSVEEN, ARNE
To: NORWEGIAN UNIVERSITY OF SCIENCE AND TECHNOLOGY (NTNU)
Reel/Frame 059759/0607 →
Priority Claims (1)
GB 1914844 · Oct 14, 2019 · national
Continuity (1)
Related Publication 20240369634A1 · Nov 7, 2024
References Cited (67)
US 10075016B2 · Wilkins · 2018 [cited by examiner]
US 10411480B2 · Garcia · 2019 [cited by examiner]
US 20090091289A1 · Nandi et al. · 2009 [cited by applicant]
US 20120001580A1 · Zhang et al. · 2012 [cited by applicant]
US 20120259563A1 · Beatty · 2012 [cited by examiner]
US 20130257049A1 · Taylor et al. · 2013 [cited by applicant]
US 20140117912A1 · Gajic · 2014 [cited by examiner]
US 20170016960A1 · Rodriguez et al. · 2017 [cited by applicant]
US 20200182684A1 · Yoskovitz · 2020 [cited by examiner]
US 20220393625A1 · He · 2022 [cited by examiner]
CN 102135600A · 2011 [cited by applicant]
CN 104535267 · 2015 [cited by applicant]
CN 106597276 · 2017 [cited by applicant]
JP S61112976A · 1986 [cited by applicant]
JP 2005251185A · 2005 [cited by applicant]
JP 2010256348A · 2010 [cited by applicant]
JP 2014512799A · 2014 [cited by applicant]
WO WO2012146613A1 · 2012 [cited by applicant]
WO WO2014117279 · 2014 [cited by applicant]
WO WO2015173662 · 2015 [cited by applicant]
WO WO201719568A1 · 2017 [cited by applicant]
WO WO2018198111 · 2018 [cited by applicant]
WO WO2021074248 · 2021 [cited by applicant]
International Search Report and Written Opinion of the International Application No. PCT/EP2020/078951 mailed Feb. 12, 2021. [cited by applicant]
Lu Dingguo et al., “Adaptive Feature Extraction and SVM Classification for Real-Time Fault Diagnosis of Drivetrain Gearboxes”, 2013 IEEE Energy Conversion Congress and Exposition, Sep. 15, 2013, pp. 3934-3940. [cited by applicant]
Tun Pyae Phyo et al., “Brushless Synchronous Generator Turn-to-Turn Short Circuit Fault Detection Using Multilayer Neural Network”, 2018 Asian Conference on Energy, Power and Transportation Electrification, Oct. 30, 201… [cited by applicant]
Kerboua A et al., “Fault Diagnosis in Induction Motor Using Pattern Recognition and Neural Networks”, 2018 International Conference on Signal, Image, Vision and Their Applications, IEEE, Nov. 26, 2018, pp. 1-7. [cited by applicant]
Pecina-Sanchez J. A. et al., “Multiple Fault Diagnosis in Variable Speed Drives Through Current Measurements”, Electrical Engineering Computing Science and Automatic Control, 2011 8 [cited by applicant]
Alvarez-Gonzalez Fernando et al., “Permanent Magnet Synchronous Machine Stator Windings Fault Detection by Hilbert-Huang Transform”, The Journal of Engineering, The Institution of Engineering and Technology, UK, vol. 20… [cited by applicant]
Ehya H et al.; Time Domain Signature Analysis of Synchronous Generator under Broken Damper Bar Fault; 45 [cited by applicant]
Bashir Mahdi Ebrahimi et al., “Dynamic Eccentricity Fault Diagnosis in Round Rotor Synchronous Motors”, Energy Conversion dn Management, Elsevier Science Publishers, Oxford GB, vol. 52, No. 5, Dec. 13, 2020, pp. 2092-20… [cited by applicant]
Bin Li et al., “Model-Free Information Extraction in Enriched Nonlinear Phase-Space”, Arxiv. Org. Cornell University Library, (Apr. 14, 2018), XP081236868. [cited by applicant]
Ferreira Jose Gregorio et al., “An Application of Machine Learning Approach to Fault Detection of a Synchronous Machine”, 2017 International Symposium on Electrical Machines, IEEE, (Jun. 18, 2017), pp. 1-6, XP033131265. [cited by applicant]
Rastko Fiser et al., “Computations of Magnetic Field Anomalies in Synchronous Generator Due to Rotor Excitation Coil Faults”, IEEE Transactions on Magnetics, IEEE Service Center, New York, vol. 49, No. 5, (May 1, 2013),… [cited by applicant]
Athira et al.; “Fault Detection and Visualization Technique for Hybrid Electric Vehicle Components”; International Conference on Power, Energy, Control and Transmissions System; Feb. 2018; pp. 159-169. [cited by applicant]
Patents Act 1977: Search Report under Section 17(5); Intellectual Property Office; Application No. GB1914844.4; Mailing Date Mar. 31, 2020; 3 pages. [cited by applicant]
Office Action; Japan Patent Office; Application No. 2022-522662; Aug. 27, 2024; 6 pages. (submitted with copy of original document and full text English translation). [cited by applicant]
China National Intellectual Property Administration, First Office Action in related CN Application 202080073898.9 mailed May 1, 2025. 14 pages (w/translation). [cited by applicant]
List of Foreign References and Their Translations, dated Jun. 9, 2025. 2 pages. [cited by applicant]
Korean Intellectual Property Office, Written Opinion, mailed Mar. 21, 2025. 49 pages (w/translation). [cited by applicant]
Ehya, H. et al.; “Pattern Recognition of Inter-Turn Short Circuit Fault in Wound Field Synchronous Generator via Stray Flux Monitoring”, 2020 International Conference on Electrical Machines (ICEM), IEEE, vol. 1, Aug. 23… [cited by applicant]
Valavi, Mostafa et al.; “Electromagnetic Analysis and electrical Signature-Based Detection of Roto Inter-Turn Faults in Salient-Pole Synchronous Machine”, IEEE Transactions on Magnetics, IEEE, vol. 54, No. 9, Sep. 1, 20… [cited by applicant]
Da, Yao et al.; “Health Monitoring, Fault Diagnosis and Failure Prognosis Techniques for Brushless Permanent Magnet Machines”, 2011 IEEE Vehicle Power and Propulsion Conference (VPPC 2011): Chicago, Illinois, USA, Sep. … [cited by applicant]
Ehya, Hossein et al.; “An Expeditious Algorithm for Identification and Classification of Rotor Faults in Salient Pole Synchronous Generators”, IEEE Transactions on Industrial Electronics, IEEE, vol. 71, No. 2, Mar. 12, … [cited by applicant]
Lipo, T.A.; “Analysis of Synchronous Machines”, 2nd Edition, CRC Press, 2012/2017. DOI: 10.1201/b12211. [cited by applicant]
Ehya, Hossein et al.; “Static and Dynamic Eccentricity Fault Diagnosis of Large Salient Pole Synchronous Generators by Means of External Magnetic Field”, IET Electric Power Applications, vol. 15, No. 7, pp. 890-902, 202… [cited by applicant]
Toliyat, H.A. et al.; “Simulation and Detection of Dynamic Air-Gap Eccentricity in Salient Pole Synchronous Machines”, IEEE Transactions On Industry Applications, vol. 35, No. 1, Jan./Feb. 1999, pp. 86-93, 1999. DOI: do… [cited by applicant]
Tabatabaei, Iman et al.; “Modeling and Simulation of a Salient-Pole Synchronous Generator with Dynamic Eccentricity Using Modified Winding Function Theory”, IEEE Transactions on Magnetics, vol. 40, No. 3, May 2004, pp. … [cited by applicant]
Babaei, Mojtaba et al.; “A Detailed Analytical Model of a Salient-Pole Synchronous Generator Under Dynamic Eccentricity Fault”, IEEE Transactions On Magnetics, vol. 47, No. 4, Apr. 2011, pp. 764-771. DOI: 10.1109/TMAG.2… [cited by applicant]
Bruzzese, Claudio; “Diagnosis of Eccentric Rotor in Synchronous Machines by Analysis of Split-Phase Currents-Part I: Theoretical Analysis”, IEEE Transactions On Industrial Electronics, vol. 61, No. 8, Aug. 2014, pp. 419… [cited by applicant]
Gyftakis, K.N. et al.; “Off-Line Detection of Static Eccentricity in Salient-Pole Synchronous Machines”, 2018 XIII International Conference on Electrical Machines (ICEM), pp. 1919-1924, 2018. DOI: 10.1109/ICELMACH.2018.… [cited by applicant]
Ehya, Hossein et al.; “Advanced Fault Detection of Synchronous Generators Using Stray Magnetic Field”, IEEE Transactions On Industrial Electronics, vol. 69, No. 11, Nov. 2022, pp. 11675-11685. DOI: 10.1109/TIE.2021.3118… [cited by applicant]
Bruzzese, Claudio et al.; “Harmonic Signatures of Static Eccentricities in the Stator Voltages and in the Rotor Current of No-Load Salient-Pole Synchronous Generators”, IEEE Transactions On Industrial Electronics, vol. … [cited by applicant]
Sadeghi, Iman et al.; “Analytic method for Eccentricity Fault Diagnosis in Salient-pole Synchronous Generators”, 2017 International Conference on Optimization of Electrical and electronic Equipment (OPTIM) & 2017 Intl' … [cited by applicant]
Kedjar, Bachir et al.; “Large Synchronous Machines Diagnosis Based on Air-Gap and Stray Fluxes—An Overview”, 2020 International Conference on Electrical Machines (ICEM), vol. 1, pp. 1384-1389. IEEE. DOI: 10.1109/ICEM499… [cited by applicant]
Lee, Sang Bin et al.; “Condition Monitoring of Industrial Electric Machines: State of the Art and Future Challenges”, IEEE Industrial Electronics Magazine, vol. 14, Iss. 4, Dec. 2020, pp. 158-167. IEEE. DOI: 10.1109/MIE… [cited by applicant]
Jiang, Chen et al.; “A Review of Condition Monitoring of Induction Motors Based on Stray Flux”, 2017 IEEE Energy Conversion Congress and Exposition (ECCE), IEEE, pp. 5424-5430, 2017. DOI: 10.1109/ECCE.2017.8096907. [cited by applicant]
Capolino, Gérard-André et al.; “State of the Art on Stray Flux Analysis in Faulted Electrical Machines”, 2019 IEEE Workshop on Electrical Machines Design Control and Diagnosis (WEMDCD), vol. 1, pp. 181-187, IEEE, 2019. … [cited by applicant]
Zamudio-Ramirez, Israel et al.; “Magnetic Flux Analysis for the Condition Monitoring of Electric Machines: A Review”, IEEE Transactions On Industrial Informatics, vol. 18, No. 5, May 2022, Apr. 2, 2021, pp. 2895-2908. D… [cited by applicant]
He, Yu-Ling et al.; “A New External Search Coil Based Method to Detect Detailed Static Air-Gap Eccentricity Position in Nonsalient Pole Synchronous Generators”, IEEE Transactions On Industrial Electronics, vol. 68, No. … [cited by applicant]
Cuevas, Mauricio et al.; “Noninvasive Detection of Winding Short-Circuit Faults in Salient Pole Synchronous Machine With Squirrel-Cage Damper”, IEEE Transactions On Industry Applications, vol. 54, No. 6, Nov./Dec. 2018,… [cited by applicant]
Cuevas, Mauricio et al.; “Non-Invasive Detection of Rotor Short-Circuit Fault in Synchronous Machines by Analysis of Stray Magnetic Field and Frame Vibrations”, IEEE Transactions On Magnetics, vol. 52, No. 7, Jul. 2016,… [cited by applicant]
Yun, Jangho et al.; “Reliable Flux-Based Detection of Field Winding Failures for Salient Pole Synchronous Generators”, IEEE Transactions On Energy Conversion, vol. 34, No. 3, Sep. 2019, pp. 1715-1718, 2019. DOI: 10.1109… [cited by applicant]
Ehya, Hossein et al.; “Pattern Recognition of Interturn Short Circuit Fault in a Synchronous Generator Using Magnetic Flux”, IEEE Transactions on Industry Applications, vol. 57, No. 4, Jul./Aug. 2021, pp. 3573-3581, 202… [cited by applicant]
Irhoumah, Miftah et al.; “Information Fusion With Belief Functions for Detection of Interturn Short-Circuit Faults in Electrical Machines Using External Flux Sensors”, IEEE Transactions On Industrial Electronics, vol. 6… [cited by applicant]
Gyftakis, Konstantinos N. et al.; “Critical Aspects of Demagnetization Faults in Multi-Stage Direct Drive Permanent Magnet Generators for Renewables”, IEEE Transactions On Industry Applications, vol. 59, No. 6, Nov./Dec… [cited by applicant]
Goktas, Taner et al.; “A Comparative Study of Current, Vibration and Stray Magnetic Flux Based Detection for Parallel Misalignment Fault in Induction Motors”, 2021 IEEE 13th International Symposium on Diagnostics for El… [cited by applicant]