The DOI matches its Crossref record; 341 of the 341 references it cites were found in a registry or an index; 24 of the 225 sources its claims cite were checked for support.
Fault Diagnosis and Fault-Tolerant Control of PMSM Drives–State of the Art and Future Challenges
Open accessAbstract
The issues of monitoring and fault diagnosis of drives with permanent magnet synchronous motors (PMSM) are currently very topical due to the increasing use of these drives in safety-critical devices. Every year, more and more articles on this subject are published. Therefore, the aim of this article is to update the overview of diagnostic methods and techniques for PMSM drives. Each of the main chapters of the article focuses on a specific element of the drive system (motor, power converter, measuring sensors), with particular emphasis on the components of the motor (stator windings, magnets, bearings, rotor). The main sections on PMSM fault diagnosis are divided according to the type of methods used to obtain the symptoms of the damage. In addition, a review of methods using the analysis of control structure signals for the diagnosis of damage to a vector-controlled motor is presented, as well as the latest achievements of researchers in the field of shallow and deep neural networks for the detection and classification of PMSM drives failures. Based on the presented literature analyses, some development trends and challenges related to the development of diagnostics and fault-tolerant control of PMSM drives are discussed in the conclusion part.
Overview
CoChat Summary
TL;DR
This IEEE Access review surveys fault diagnosis and fault-tolerant control (FTC) for permanent magnet synchronous motor (PMSM) drives, covering motor, converter, and sensor faults and methods based on signal analysis, mathematical models, control-structure signals, and artificial intelligence. It synthesizes the literature and identifies future challenges in transient diagnostics, multiple-fault diagnosis, AI/deep learning, hardware implementation, and prognostics.
Key findings
- The review classifies PMSM faults into electrical, magnetic, and mechanical types and cites component failure statistics: stator winding failures account for 36–66% of AC motor breakdowns, bearing faults 13–41%, bearing failures about 40–50% of all electric motor failures, power semiconductor device damages about 35% of all adjustable-speed-drive faults, DC-link capacitors about 30% of frequency-converter failures, and transistor failures 12% of all electric-drive failures.
- Signal-analysis methods dominate PMSM diagnostics: FFT/MCSA/EPVA are widely used for inter-turn short circuits (ITSCs) and demagnetization, while time-frequency methods such as STFT, WT, WVD, CWD, and HHT address non-stationary conditions; control-structure signals can enable sensorless diagnostics but are sensitive to controller bandwidth.
- AI-based diagnostics are reviewed: shallow neural networks (MLP, RBF, SOM, PNN, BNN) require preprocessing, while deep networks (CNN, LSTM) allow direct feature extraction; Table IX reports literature classification accuracies such as MLP 99.02% on vibrations, CNN 99.38% on flux, CNN 99.28% on stator currents, and SOM 93.00% on vibrations.
- FTC is divided into passive and active approaches; active FTC uses fault detection and diagnosis with reconfiguration or compensation, speed-sensor FTC relies on sensorless estimators, current-sensor FTC uses observers, and inverter FTC often uses hardware redundancy; ITSC-FTC strategies remain relatively rare and mostly target torque-ripple or copper-loss reduction, with few limiting short-circuit current.
Methods
- Design: state-of-the-art review/survey; it compares itself with existing PMSM diagnostic surveys in Table I and organizes the literature by fault location and diagnostic method.
- Data or sample: no primary experimental sample; it analyzes published methods and presents tabular summaries (Tables II–X) for ITSC, demagnetization, bearing, eccentricity, unbalance, misalignment, converter, sensor faults, AI methods, and FTC.
- Main analysis: categorizes methods into frequency-domain, time-frequency, time-domain/statistical, model-based, control-structure-signal, and AI-based approaches, discussing advantages, disadvantages, and future trends.
Limitations
- Paper-stated: future challenges include diagnostics during transients, hardware implementation, failure prediction/prognostics, data storage and cloud transfer, multiple-fault diagnosis, AI/deep-learning development for PMSM drives, transfer learning, and real-time fault detection.
- Paper-stated: many PMSM fault diagnosis methods lack hardware implementation; deep neural networks are limited by structural complexity; few papers address ITSC-FTC and fault-current mitigation; control-structure-based mechanical fault diagnosis needs further work.
- Evident from the text: as a review, it reports no new experimental validation; some cited methods are simulation-only or inconclusive (e.g., DWT+NN bearing diagnosis in DTC is described as simulation-only and rather inconclusive), and the AI accuracy table is literature-derived rather than a controlled benchmark.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures

















Verification
Claims the paper makes
19 Valid · 20 Not valid · 149 Not checked · 149 Own results and interpretations
At least one cited source doesn’t support this claim or points to a different paper, and none confirmed it — see the verdicts below.
In the paper
“Greater sensitivity of this component to the stator winding fault compared to the FFT of the stator phase current is also emphasized.”
§ Fault diagnosis and fault-tolerant control of PMSM drivesstate of the art and future challenges > A. FREQUENCY DOMAIN METHODS
What the sources say
- Disputedcites [43] sourceExperimental — accuracy not yet measured
Section 5 (page not provided) compares the fault indicators and identifies the 3fs component in the FFT spectrum of the stator phase current—not the 2fs component—as the most sensitive across the tested load-torque range. The Conclusions likewise describe both indicators as sensitive, without saying that 2fs is more sensitive. (LLM, conf=0.88)
Checked by a reasoning model — may be wrong.
- Not matchedcites [45]- [47]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Disputed
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“According to [20], the greatest and most obvious increase in the case of this fault is the increase in the amplitude of the 3fs component, which has also been confirmed by the results presented by the authors in [42] and [43].”
§ Fault diagnosis and fault-tolerant control of PMSM drivesstate of the art and future challenges > A. FREQUENCY DOMAIN METHODS
What the sources say
- Partly supportedcites [20] sourceExperimental — accuracy not yet measured
Section 3.2.1 (Frequency Domain Methods) says that for an inter-turn short circuit, the most obvious feature is an increase in the third-harmonic amplitude, corresponding to 3fs. It does not establish that this is the greatest increase in magnitude among the components. (LLM, conf=0.83)
- Partly supportedcites [42] sourceExperimental — accuracy not yet measured
Section 6 (Conclusions; page not available in our copy) reports that inter-turn short circuits increase the stator current’s 3fs harmonic and that its amplitude is much greater under field-oriented control than under scalar control. It does not establish that this is the greatest increase among fault-related components; the claim also omits the control-structure qualification. (LLM, conf=0.83)
- Supportedcites [43] source
Section 6 (Conclusions; page not provided) calls the increase in the 3fs component’s amplitude the most significant symptom of stator-winding damage. Section 4.1 also reports a large increase in that component after an interturn short circuit. (LLM, conf=0.94)
boostedstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“In all of these papers, the Authors conclude that the increase of the 2fs component amplitude in the stator phase current space vector module spectrum is a symptom of a stator winding fault.”
§ Fault diagnosis and fault-tolerant control of PMSM drivesstate of the art and future challenges > A. FREQUENCY DOMAIN METHODS
What the sources say
- Supportedcites [43] source
Section 2.2 states that, following an inter-turn short-circuit, the 2fs component increases in the FFT spectrum of the stator phase current space vector magnitude. This directly supports the attributed symptom of a stator winding fault. (LLM, conf=0.93)
- Not matchedcites [45]- [47]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
boostedstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“The limitation of this approach is mentioned in [60] to measure the ZSVC, the access to the neutral point of the stator winding is needed.”
§ Fault diagnosis and fault-tolerant control of PMSM drivesstate of the art and future challenges > A. FREQUENCY DOMAIN METHODS
What the sources say
- Supportedcites [60] source
The Conclusion explicitly states that an accessible neutral point of the stator windings is needed to measure the ZSVC. It also notes that this condition is met in a fault-tolerant PMSM drive system. (LLM, conf=0.95)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“The basic diagnostic signals in eccentricity diagnosis are: stator current [135], [143]- [146], [150], [151], [156]- [159], [161], [162], mechanical vibrations [149], [155], [156], noise [155], an airgap search coil voltage [149], [152], [156], [160], stator voltage [159], speed [159], load torque [159], d-axis stator inductance Ld [147], [148], BEMF [160] and unbalanced magnetic pull [153], [154]”
§ Fault diagnosis and fault-tolerant control of PMSM drivesstate of the art and future challenges > B. ECCENTRICITY FAULTS
What the sources say
- Not checked — no full text of the sourcecites [135] source
- Not matchedcites [143]-[146]
Couldn’t be matched to a paper in Crossref, so it can’t be checked.
- Supportedcites [150] source
This source is cited within the stator-current group of references, not for the entire list of signals. The Introduction identifies stator current as a prevalent monitored signal for motor fault detection, and Section 5 analyzes it for static eccentricity diagnosis in LSPMSMs. Page numbers are not available in our copy. (LLM, conf=0.93)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
150 more claims · 5 with their cited sources checked
Create a free account to see all 337 claims and to verify the 1 reference still open.
- It may state two separate claims as one. 113
- Probably not a substantial claim. 91
- The quote only partly states this claim. 3
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Fault diagnosis and fault-tolerant control of PMSM drivesstate of the art and future challenges > C. DEEP NEURAL NETWORKS APPLICATION IN PMSM DRIVES
“The possibility of direct extraction of the input signal features in the diagnostics of PMSM stator windings faults has been described in [220], [222], [223], [229], [237].”
§ Fault diagnosis and fault-tolerant control of PMSM drivesstate of the art and future challenges > B. SHALLOW NEURAL NETWORKS APPLICATION IN PMSM DRIVES
“[237] + + CNN FFT IsABC”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Fault diagnosis and fault-tolerant control of PMSM drivesstate of the art and future challenges > TABLE I COMPARISON OF THIS PAPER WITH EXISTING SURVEYS AND REVIEW PAPERS ON DIAGNOSTICS OF PMSM DRIVES
“[15] 2015 125 (120) 1997-2016”
§ Fault diagnosis and fault-tolerant control of PMSM drivesstate of the art and future challenges > References
“15. M. Cheng, J. Hang, and J.Zhang, "Overview of fault diagnosis theory and method for permanent magnet machine," Chinese Journal of Electrical Eng., vol. 1 no. 1, pp. 21-36, 2015..”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Fault diagnosis and fault-tolerant control of PMSM drivesstate of the art and future challenges > IX. FAULT DETECTION OF PMSM DRIVE COMPONENTS AND FAULT-TOLERANT CONTROL A. FREQUENCY CONVERTER FAULTS
“The voltage-based method was also applied in [274] for open switch fault diagnosis in a voltage-oriented controlled AC/DC line side converter.”
§ Fault diagnosis and fault-tolerant control of PMSM drivesstate of the art and future challenges > References
“274. M. Bourogaoui, H. B. A. Sethom, and I. S. Belkhodja. "Speed/position sensor fault tolerant control in adjustable speed drives -a review." ISA Transactions, vol. 64, pp. 269-284, 2016.”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Fault diagnosis and fault-tolerant control of PMSM drivesstate of the art and future challenges > B. SHALLOW NEURAL NETWORKS APPLICATION IN PMSM DRIVES
“[216] + MLP DIRECT IsABC”
§ Fault diagnosis and fault-tolerant control of PMSM drivesstate of the art and future challenges > C. DEEP NEURAL NETWORKS APPLICATION IN PMSM DRIVES
“[216] + + MLP 98,50% (FFT) IsABC + Te + + MLP 96,10% (STAT) IsABC + Te”
Citations
Cites
Condition Monitoring and Fault Diagnosis of Electrical Motors—A Review
Nandi, S., Toliyat, H. A., & Li, X. (2005) · IEEE Transactions on Energy Conversion · doi:10.1109/tec.2005.847955 · Cited by 2,382
A review of induction motors signature analysis as a medium for faults detection
El Hachemi Benbouzid, M. (2000) · IEEE Transactions on Industrial Electronics · doi:10.1109/41.873206 · Cited by 1,602
Condition Monitoring for Device Reliability in Power Electronic Converters: A Review
Yang, S., Xiang, D., Bryant, A., Mawby, P., Ran, L., & Tavner, P. (2010) · IEEE Transactions on Power Electronics · doi:10.1109/tpel.2010.2049377 · Cited by 1,278 · cited 1×
“According to [238], [239], power semiconductor device damages account for approximately 35% of all ASD faults.”
BackgroundAdvances in Diagnostic Techniques for Induction Machines
Bellini, A., Filippetti, F., Tassoni, C., & Capolino, G.-A. (2008) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2008.2007527 · Cited by 1,140 · cited 1×
“Additionally, the FFT can even mask components that appear at a given moment of time but are of very short duration [10], [32].”
BackgroundA Literature Review of IGBT Fault Diagnostic and Protection Methods for Power Inverters
Lu, B., & Sharma, S. K. (2009) · IEEE Transactions on Industry Applications · doi:10.1109/tia.2009.2027535 · Cited by 985
A High-Speed Sliding-Mode Observer for the Sensorless Speed Control of a PMSM
Kim, H., Son, J., & Lee, J. (2011) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2010.2098357 · Cited by 733 · cited 3×
“In [283] the SMO was developed with sign-type switching function replaced by a sigmoid function with some boundary”
BackgroundMethodWelchko, B. A., Lipo, T. A., Jahns, T. M., & Schulz, S. E. (2004) · IEEE Transactions on Power Electronics · doi:10.1109/tpel.2004.830074 · Cited by 724 · cited 2×
“A detailed overview of fault-tolerant inverter topologies is presented in [307], [308].”
BackgroundNew Sliding-Mode Observer for Position Sensorless Control of Permanent-Magnet Synchronous Motor
Qiao, Z., Shi, T., Wang, Y., Yan, Y., Xia, C., & He, X. (2013) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2012.2206359 · Cited by 602 · cited 2×
“These could be: extended observer [279], SMO [280], [283], [284] or super-twisting sliding mode observer (ST-SMO) [285], MRAS estimator [281], KF [282]”
BackgroundMethodTrends in Fault Diagnosis for Electrical Machines: A Review of Diagnostic Techniques
Henao, H., Capolino, G.-A., Fernandez-Cabanas, M., Filippetti, F., Bruzzese, C., Strangas, E., Pusca, R., Estima, J., Riera-Guasp, M., & Hedayati-Kia, S. (2014) · IEEE Industrial Electronics Magazine · doi:10.1109/mie.2013.2287651 · Cited by 602 · cited 3×
“The popularity of this method is related to its simplicity, low cost and online machine state monitoring capabilities [11].”
MethodReport of Large Motor Reliability Survey of Industrial and Commercial Installations, Part I
(1985) · IEEE Transactions on Industry Applications · doi:10.1109/tia.1985.349532 · Cited by 602
Research works printed but not linked: 7
- Krichen, Fault detection and diagnosis methods in permanent magnet synchronous machines: A review, 229
- Varal, 2017, Bearing fault analysis of permanent magnet synchronous motor (PMSM) using current signature analysis, Int. Res. J. Eng. Technol., 4, 410
- Abbas, 2014, Bearings fault diagnosis in direct torque control permanent magnet synchronous motor based on discrete wavelet transform and artificial neural network, Int. J. Adv. Eng. Technol., 7, 341
- 10.1049/iet-epa.2012.0316 · DOI · Paper page
- 10.1109/TIE.2017.2688973 · DOI · Paper page
- 10.1109/TEC.2017.2726142 · DOI · Paper page
- 10.1109/TEC.2019.2936225 · DOI · Paper page
Cited by
Pietrzak, P., & Wolkiewicz, M. (2023) · Sensors · doi:10.3390/s23041757 · Cited by 74
“Damage to PMs can be divided into mechanical damage of the PM (cracks, chipping) and those associated with the phenomenon of demagnetization [1,8].”
BackgroundSelf-citationCheng, M., Zhou, J., Qian, W., Wang, B., Zhao, C., & Han, P. (2024) · Chinese Journal of Electrical Engineering · doi:10.23919/cjee.2023.000048 · Cited by 80
El-Dalahmeh, M., Al‐Greer, M., Bashir, I., et al. (2023) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2023.108894 · Cited by 64
Mueller, P. N., Woelfl, L., & Can, S. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.106834 · Cited by 54
Fault Diagnosis of Electric Motors by a Channel-Wise Regulated CNN and Differential of STFT
Mohammad‐Alikhani, A., Jamshidpour, E., Dhale, S., Akrami, M., Pardhan, S., & Nahid‐Mobarakeh, B. (2025) · IEEE Transactions on Industry Applications · doi:10.1109/tia.2025.3532556 · Cited by 53
Metadata
- Authors
- Orlowska-Kowalska, T., Wolkiewicz, M., Pietrzak, P., Skowron, M., Ewert, P., Tarchala, G., Krzysztofiak, M., & Kowalski, C. T.
- Affiliations
- Department of Electrical Machines, Drives and Measurements, Wrocław University of Science and Technology, Wrocław, Poland
- Wrocław University of Science and Technology (PL)
- ORCID
- Venue
- IEEE Access
- Published
- 2022
- Volume
- 10
- Pages
- 59979-60024
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W4285271556
- Semantic Scholar
- dc069ddc2dd7fed25b6db8df368599dab4ad9d8b
- Cited by
- 328
- References
- 335
- Citations by year
- 2026: 72 · 2025: 112 · 2024: 81 · 2023: 52 · 2022: 11
- FWCI
- 21.95
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- IEEE Access (publishedVersion, cc-by-nc-nd)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
- Funders
- National Science Centre Poland (2017/27/B/ST7/00816)
- Topics
- Physical Sciences › Engineering › Control and Systems Engineering › Machine Fault Diagnosis Techniques
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Sensorless Control of Electric Motors
- Physical Sciences › Engineering › Control and Systems Engineering › Fault Detection and Control Systems
- Keywords
- permanent magnet synchronous motor, fault diagnosis, fault-tolerant control, motor drives, stator winding faults, bearing defects, rotor faults, power converter faults, sensor faults, artificial neural networks, safety-critical systems
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-06, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-06 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Fault Diagnosis and Fault-Tolerant Control of PMSM Drives–State of the Art and Future Challenges. https://app.cochat.ai/papers/10.1109/access.2022.3180153
- The paper
- Orlowska-Kowalska, T., Wolkiewicz, M., Pietrzak, P., Skowron, M., Ewert, P., Tarchala, G., Krzysztofiak, M., & Kowalski, C. T. (2022). Fault Diagnosis and Fault-Tolerant Control of PMSM Drives–State of the Art and Future Challenges. IEEE Access. https://doi.org/10.1109/access.2022.3180153
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.