A health image for deep learning-based fault diagnosis of a permanent magnet synchronous motor under variable operating conditions: Instantaneous current residual map

Park, Chan Hee; Kim, Hyeongmin; Suh, Chaehyun; Chae, Minseok; Yoon, Heonjun; Youn, Byeng D.

doi:10.1016/j.ress.2022.108715

Cited by 32 publications

(7 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To validate the proposed approach, wind turbine and gearbox systems are considered as two case studies. In the same context, to ensure the reliable operation of permanent magnet synchronous motors (PMSMs) under variable operating conditions, a novel robust CNN-based diagnosis model was proposed in [ 40 ]. The core idea behind the research is to consider the fault-related information in the transformed motor current signals for 2D instantaneous current residual images.…”

Section: Related Workmentioning

confidence: 99%

GRU-Based Denoising Autoencoder for Detection and Clustering of Unknown Single and Concurrent Faults during System Integration Testing of Automotive Software Systems

Abboush

Knieke

Rausch

2023

Sensors

View full text Add to dashboard Cite

Recently, remarkable successes have been achieved in the quality assurance of automotive software systems (ASSs) through the utilization of real-time hardware-in-the-loop (HIL) simulation. Based on the HIL platform, safe, flexible and reliable realistic simulation during the system development process can be enabled. However, notwithstanding the test automation capability, large amounts of recordings data are generated as a result of HIL test executions. Expert knowledge-based approaches to analyze the generated recordings, with the aim of detecting and identifying the faults, are costly in terms of time, effort and difficulty. Therefore, in this study, a novel deep learning-based methodology is proposed so that the faults of automotive sensor signals can be efficiently and automatically detected and identified without human intervention. Concretely, a hybrid GRU-based denoising autoencoder (GRU-based DAE) model with the k-means algorithm is developed for the fault-detection and clustering problem in sequential data. By doing so, based on the real-time historical data, not only individual faults but also unknown simultaneous faults under noisy conditions can be accurately detected and clustered. The applicability and advantages of the proposed method for the HIL testing process are demonstrated by two automotive case studies. To be specific, a high-fidelity gasoline engine and vehicle dynamic system along with an entire vehicle model are considered to verify the performance of the proposed model. The superiority of the proposed architecture compared to other autoencoder variants is presented in the results in terms of reconstruction error under several noise levels. The validation results indicate that the proposed model can perform high detection and clustering accuracy of unknown faults compared to stand-alone techniques.

show abstract

Section: Related Workmentioning

confidence: 99%

GRU-Based Denoising Autoencoder for Detection and Clustering of Unknown Single and Concurrent Faults during System Integration Testing of Automotive Software Systems

Abboush

Knieke

Rausch

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…These unstable excitations and complex noisy conditions directly contribute to challenges in extracting fault characteristic signals from the driving motor of artillery. Common motor faults are usually detected using vibration, magnetic, and curren signals [5][6][7]. Vibration signal detection has obvious fault characteristics and possesses high level of detection accuracy for mechanical faults, e.g., motor bearing faults [8][9][10] Magnetic signals are sensitive to flux changes caused by any magnetic field imbalance and have recently become an important area of research [11,12].…”

Section: Introductionmentioning

confidence: 99%

“…Zhao et al [27] designed a filter denoising network and trained the filte threshold using the deep residual shrinkage networks network. In light of the exceptiona anti-noise capabilities offered by fusion wavelet and deep learning methodologies, thi Common motor faults are usually detected using vibration, magnetic, and current signals [5][6][7]. Vibration signal detection has obvious fault characteristics and possesses a high level of detection accuracy for mechanical faults, e.g., motor bearing faults [8][9][10].…”

Section: Introductionmentioning

confidence: 99%

Fault Diagnosis Methods for an Artillery Loading System Driving Motor in Complex Noisy Environments

Huang,

Li,

Tang

et al. 2024

Sensors

View full text Add to dashboard Cite

With the development of modern military technology, electrical drive technology has become a power source for modern artillery. In fault monitoring of a driving motor mounted on a piece of artillery, various sensors are susceptible to interference from the complex environment, both inside and outside the artillery itself. In this study, we creatively propose a fault diagnosis model based on an attention mechanism, the AdaBoost method and a wavelet noise reduction network to address the difficulty in obtaining high-quality motor signals in complex noisy interference environments. First, multiple fusion wavelet basis, soft thresholding, and index soft filter optimization were used to train multiple wavelet noise reduction networks that could recover sample signals under different noise conditions. Second, a convolutional neural network (CNN) classification module was added to construct end-to-end classification models that could correctly identify faults. The above basis classification models were then integrated into the AdaBoost method with an improved attention mechanism to develop a fault diagnosis model suitable for complex noisy environments. Finally, two experiments were conducted to validate the proposed method. Under motor signals with varying signal-to-noise ratios (SNRs) noises, the proposed method achieved an average accuracy of 92%, surpassing the conventional method by over 8.5%.

show abstract

“…The comprehensive reviews of motor fault detection techniques are given in reference [6][7][8][9][10]. In recent years, fault detection techniques based on signal processing have been increasingly used, such as frequency domain analysis, time domain analysis, and frequency-time analysis [11][12][13][14][15].…”

Section: Introductionmentioning

confidence: 99%

Adaptive Parameter Selection Variational Mode Decomposition Based on Bayesian Optimization and Its Application to the Detection of ITSC in PMSM

Xia,

Wang,

2024

IEEE Access

View full text Add to dashboard Cite

Permanent magnet synchronous motor (PMSM) is a vital component of modern industry which is widely used in transport, aerospace and intelligent machinery. In the light of its relatively high frequency of inter-turn short circuit (ITSC) fault, it is valuable to detect the fault accurately and efficiently. Due to the convenience of motor vibration signal measurement, more attention has been paid to fault detection methods based on vibration signal. As a nonstationary, nonlinear signal, vibration signal is highly susceptible to external noise interference. Variational mode decomposition (VMD) has a wide range of applications in the field of nonlinear signal analysis, but the processing ability to the signal is affected by the parameter setting. Hence, a Bayesian optimized adaptive parameter selection variational mode decomposition (BOAPS-VMD) signal processing method is proposed and applied to detect the ITSC in PMSM. Firstly, the motor vibration signal is decomposed through BOAPS-VMD, and the intrinsic mode functions (IMFs) are obtained. Secondly, the cumulative variance contribution rate (C-VCR) is applied to identify the IMFs that contain fault signature information. Finally, using Hilbert transform (HT) to further analyze the IMFs that are identified. The results are output in 3D time-frequency diagrams to enhance the representation of fault signatures. The effectiveness and accuracy of the BOAPS-VMD were validated through the finite element simulation and experiment. The study shows that the BOAPS-VMD effectively improves the modal mixing phenomenon, has better noise robustness, improves the accuracy of fault detection, and has better engineering applicability.INDEX TERMS Permanent magnet synchronous motor (PMSM), fault detection, variational mode decomposition (VMD), Bayesian optimization, Hilbert transform (HT)

show abstract

A health image for deep learning-based fault diagnosis of a permanent magnet synchronous motor under variable operating conditions: Instantaneous current residual map

Cited by 32 publications

References 31 publications

GRU-Based Denoising Autoencoder for Detection and Clustering of Unknown Single and Concurrent Faults during System Integration Testing of Automotive Software Systems

GRU-Based Denoising Autoencoder for Detection and Clustering of Unknown Single and Concurrent Faults during System Integration Testing of Automotive Software Systems

Fault Diagnosis Methods for an Artillery Loading System Driving Motor in Complex Noisy Environments

Adaptive Parameter Selection Variational Mode Decomposition Based on Bayesian Optimization and Its Application to the Detection of ITSC in PMSM

Contact Info

Product

Resources

About