Open Switch Fault Diagnosis Method for PWM Voltage Source Rectifier Based on Deep Learning Approach

Shi, Tiancheng; He, Yigang; Wang, Tao; Li, Bing

doi:10.1109/access.2019.2917311

Cited by 42 publications

(22 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As explained in Section II, RBM-based and AE-based models can be trained in two steps: layer-wise pretraining, and fine-tuning on the network by stacking previously learned layers. Using this strategy, several researchers built regular DBNs [153]- [159] and AEs [160]- [163] for fault diagnosis; [153]- [155], [160] emphasized network hyperparameter tuning. Note that the layer-wise pretraining step is typically unsupervised, and the pretrained network serves as an initialization to the whole model.…”

Section: ) Structured Datamentioning

confidence: 99%

A Review on Deep Learning Applications in Prognostics and Health Management

et al. 2019

View full text Add to dashboard Cite

Deep learning has attracted intense interest in Prognostics and Health Management (PHM), because of its enormous representing power, automated feature learning capability and best-in-class performance in solving complex problems. This paper surveys recent advancements in PHM methodologies using deep learning with the aim of identifying research gaps and suggesting further improvements. After a brief introduction to several deep learning models, we review and analyze applications of fault detection, diagnosis and prognosis using deep learning. The survey validates the universal applicability of deep learning to various types of input in PHM, including vibration, imagery, time-series and structured data. It also reveals that deep learning provides a one-fits-all framework for the primary PHM subfields: fault detection uses either reconstruction error or stacks a binary classifier on top of the network to detect anomalies; fault diagnosis typically adds a soft-max layer to perform multi-class classification; prognosis adds a continuous regression layer to predict remaining useful life. The general framework suggests the possibility of transfer learning across PHM applications. The survey reveals some common properties and identifies the research gaps in each PHM subfield. It concludes by summarizing some major challenges and potential opportunities in the domain.

show abstract

Section: ) Structured Datamentioning

confidence: 99%

A Review on Deep Learning Applications in Prognostics and Health Management

et al. 2019

View full text Add to dashboard Cite

show abstract

“…The length of the current for the diagnostic accuracy for a random vector functional network (RVFL) has been discussed in [126], which shows high accuracy can be achieved if the current length exceeds 60 ms. Besides, the double chain quantum genetic algorithm can be utilized to optimise the current length and the denoising sparse autoencoder can extract the fault feature automatically [127], [128]. In [129], each phase current is shifted by 120 degrees and 240 degrees and performed the Clark transformation to generate the direct currents in d-q axis.…”

Section: A: Feature Extractionmentioning

confidence: 99%

Ensuring a Reliable Operation of Two-Level IGBT-Based Power Converters: A Review of Monitoring and Fault-Tolerant Approaches

Liu

Yang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

Despite the emerging multi-phase and multi-level converters, two-level insulated gate bipolar transistor-based power converters are still widely used in industrial applications in nowadays. Thus, its reliability is of significant importance for ensuring industrial safety. In this paper, a review of the possibilities to ensure the reliable operation of these power converters is presented. The possible approaches are categorized into two groups: condition monitoring and fault-tolerant control. The former approach performs the monitoring methods of power converters, which enables the identification of device degradation to be realized. Accordingly, the mechanisms, indicators, and measuring methods of degradation are demonstrated in this paper to assist the design of condition-based maintenance. In contrast, the latter approach is a postfault one, where power converters remain the operation by activating the fault-tolerant units after faults are identified. For this approach, fault detection, fault isolation, and tolerant strategies are essential. Finally, the performance and cost-effectiveness of the two categories are discussed in this paper. INDEX TERMS Two-level power converter, reliability, condition Monitoring, fault tolerance, renewable energy application, insulated gate bipolar transistor.

show abstract

“…Several fault detection methods have been proposed recently [20]- [22], [25]- [28]. In [20], a detection algorithm based on the fault harmonic signature of the DC-link output voltage is presented for seven different classes of O/C faults.…”

Section: Introductionmentioning

confidence: 99%

“…Comparing the harmonics of the DC voltage before and during the fault to identify if the fault is in the stator or in the rectifier. In [28] a fault diagnosis analysis based on ANN is proposed for voltage source rectifier. The drawback is the need of enough historical failure data to train ANN, the three current vectors are used to train the ANN.…”

Section: Introductionmentioning

confidence: 99%

Open-Circuit Fault Diagnosis and Maintenance in Multi-Pulse Parallel and Series TRU Topologies

Saura

Bakkar

Bogarra

2020

IEEE Trans. Power Electron.

View full text Add to dashboard Cite

Transformer Rectifier Units (TRUs) are a reliable way for DC generation in several electric applications. These units are formed by multiple three-phase uncontrolled bridge rectifiers connected according to two main topologies (parallel and series), and fed by a phase-shifting transformer, which can have different configurations. Fault diagnosis of the uncontrolled bridge rectifier diodes is one of the most important concerns on the electronic devices, nonetheless, rectifier units are inherently not protected in front of Open-Circuit (O/C) faults, which cause malfunction and performance deterioration. In order to solve this drawback, the proposed fault diagnosis method is based on the O/C fault signature observed in the DC-link output voltage of TRUs rectifier. It allows detecting the O/C diodes of parallel and series TRUs with different phase-shifting transformer configurations and for the most usual fault scenarios. Moreover, it also helps the prediction of diodes that could be exposed to failure after the fault, which provides corrective maintenance for the TRU development. The proposed method is illustrated from MATLAB TM numerical simulations of a 12-pulse TRU, and is validated with experimental tests.

show abstract

Open Switch Fault Diagnosis Method for PWM Voltage Source Rectifier Based on Deep Learning Approach

Cited by 42 publications

References 43 publications

A Review on Deep Learning Applications in Prognostics and Health Management

A Review on Deep Learning Applications in Prognostics and Health Management

Ensuring a Reliable Operation of Two-Level IGBT-Based Power Converters: A Review of Monitoring and Fault-Tolerant Approaches

Open-Circuit Fault Diagnosis and Maintenance in Multi-Pulse Parallel and Series TRU Topologies

Contact Info

Product

Resources

About