A generalized approach for intelligent fault detection and recovery in power electronic systems

Chen, Weiqiang; Bazzi, Ali M.

doi:10.1109/ecce.2013.6647311

Cited by 16 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Energies 2021, 14,7668 where Vin_pk is the peak value of the measured Vin and Vin_pk_MAX = 500 V. This last value has been selected according to the common rules and values of disturbance levels typical of the electromagnetic compatibility immunity tests [30].…”

Section: The Proposed Fdi/ifdi Schemementioning

confidence: 99%

“…Primarily, there are two categories of methods: (i) model-based methods in which the data coming from the real components are analyzed and compared with the outputs of the models of the healthy components and (ii) data-based methods in which the data coming from the real components are compared with the stored data measured on the healthy real physical components [12]. Various fault detection and diagnosis approaches are investigated based on threshold methods [13], fuzzy logic methods [14], domain transformation methods (Fourier transform, wavelet transform) [15], classification methods (decision tree, feature extraction, support vector machine classifier, neural network classifier) [16], and state estimation methods [17].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Fault Diagnostic Scheme for Predictive Maintenance of AC/DC Converters in MV/LV Substations

et al. 2021

View full text Add to dashboard Cite

The reliability of systems and components is a fundamental need for the efficient development of a smart distribution grid. In fact, the presence of a fault in one component of the grid could potentially lead to a service interruption and loss of profit. Since faults cannot be avoided, the introduction of a diagnostic scheme could predict the fault of a component in order to carry out predictive maintenance. In this framework, this paper proposes a novel Fault Detection and Isolation (FDI) scheme for AC/DC converters in MV/LV substations. In order to improve the reliability of the FDI procedure, the system architecture includes also an Instrument Fault Detection and Isolation section for identifying faults that could occur on the instruments and sensors involved in the monitoring process of the AC/DC converter. The proposed architecture is scalable, easily upgradable, and uses cost-effective sensors. Tests, carried out on a real test site, have demonstrated the efficacy of the proposal showing very good IFDI diagnostic performance for the 12 types of faults tested. Furthermore, as the FDI diagnostic performance regards, it shows a detection rate close to 100%.

show abstract

Section: The Proposed Fdi/ifdi Schemementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A Fault Diagnostic Scheme for Predictive Maintenance of AC/DC Converters in MV/LV Substations

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The proceeding of a neural network starts from the system activated by the input layer where the input data are weighted, and then neurons in the hidden layer perform a user chosen computation method and continue to activate all neurons to the end of this layer. Finally, the output layer determines which characteristics should be read [31,32].…”

Section: The Training Of the Mlpmentioning

confidence: 99%

“…After supervised learning of neurons is over, the trained networks are stored to be used in the algorithm. Whenever an image is taken as input to the algorithm, then simulated by the trained network and from the results; a percentage can be given to which diagnosis should be taken from the data set [22,31].…”

Section: The Training Of the Mlpmentioning

confidence: 99%

IC testing using thermal image based on intelligent classification methods

Al-Obaidy¹

2021

Preprint

View full text Add to dashboard Cite

The goal of this thesis is to propose an algorithm which would can locate the defect IC on the PCB during their manufacturing phase based on a thermal image. A 3-dimensional PCB finite-element model is developed to estimate the temperature profile of stacked ICs. Image processing by noise removing and region of interest segmentation are applied. Two sets of feature extraction are presented; first-order histogram features and Gray Level Co-occurrence Matrix (GLCM) features. The Principle Component Analysis (PCA) method is applied to decrease the feature's extractions into smallest uncorrelated input. Three main intelligent techniques; Multilayer Perceptron (MLP), Support Vector Machine (SVM), and Adaptive Neuro-Fuzzy Inference System (ANFIS) are used to classify the thermal conditions of ICs into normal and faulty status. On validation, the proposed approach applies to do thermal testing on Arduino UNO. The experimental evaluation is performed to detect the fault condition on the real time operating PCB.

show abstract

“…For each power electronic component, open-and short-circuit faults were injected, and diverse voltage was observed. Intelligent control was utilized to engage redundant components to fault recovery [22]. Ding et al presented fault detection and isolation filters for three-phase AC-DC electronic systems [23].…”

Section: Related Workmentioning

confidence: 99%

Fault Detection and Classification with Optimization Techniques for a Three-Phase Single-Inverter Circuit

Gomathy¹,

Selvaperumal²

2016

Journal of Power Electronics

View full text Add to dashboard Cite

Fault detection and isolation are related to system monitoring, identifying when a fault has occurred, and determining the type of fault and its location. Fault detection is utilized to determine whether a problem has occurred within a certain channel or area of operation. Fault detection and diagnosis have become increasingly important for many technical processes in the development of safe and efficient advanced systems for supervision. This paper presents an integrated technique for fault diagnosis and classification for open-and short-circuit faults in three-phase inverter circuits. Discrete wavelet transform and principal component analysis are utilized to detect the discontinuity in currents caused by a fault. The features of fault diagnosis are then extracted. A fault dictionary is used to acquire details about transistor faults and the corresponding fault identification. Fault classification is performed with a fuzzy logic system and relevance vector machine (RVM). The proposed model is incorporated with a set of optimization techniques, namely, evolutionary particle swarm optimization (EPSO) and cuckoo search optimization (CSO), to improve fault detection. The combination of optimization techniques with classification techniques is analyzed. Experimental results confirm that the combination of CSO with RVM yields better results than the combinations of CSO with fuzzy logic system, EPSO with RVM, and EPSO with fuzzy logic system.

show abstract

A generalized approach for intelligent fault detection and recovery in power electronic systems

Cited by 16 publications

References 12 publications

A Fault Diagnostic Scheme for Predictive Maintenance of AC/DC Converters in MV/LV Substations

A Fault Diagnostic Scheme for Predictive Maintenance of AC/DC Converters in MV/LV Substations

IC testing using thermal image based on intelligent classification methods

Fault Detection and Classification with Optimization Techniques for a Three-Phase Single-Inverter Circuit

Contact Info

Product

Resources

About