Patents
Literature
Hiro is an intelligent assistant for R&D personnel, combined with Patent DNA, to facilitate innovative research.
Hiro

122 results about "Power electronic circuit" patented technology

Method for detecting open-circuit fault of inverter circuit

ActiveCN103364683AEasy to judgeImplement nonlinear mappingElectrical testingPhase shiftedTransducer
The invention discloses a method for detecting the open-circuit fault of an inverter circuit. The method comprises the following steps of: (1) defining fault characteristic quantities, wherein the three fault characteristic quantities are available in the method and respectively represent different meanings; (2) computing a three-phase voltage fundamental current amplitude, carrying out the phase shift and the Park conversion on the obtained three-phase voltage in a sampling way respectively, obtaining the size of the fundamental current amplitude by a conversion result, and filtering by a digital filter in the process; (3) detecting the fault of a neural network, and outputting the former two characteristic quantities through the BP (pressure transducer) neural network by the computation result in the step (2); and (4) positioning a fault power tube, testing the maximum value and the minimum value of the obtained three-phase voltage in a sampling way respectively, obtaining the specific position of the fault power tube through simple logical judgment, and outputting the third fault characteristic quantity. According to the method disclosed by the invention, the fault information of the power tube of the inverter circuit can be quickly and exactly obtained only by analyzing the output three-phase voltage, and the method can be realized only by a software algorithm without adding other outer hardware circuits, so that the cost can be reduced, the efficiency can be improved, the method is higher in application ability, and the method has the application value for researching the real-time fault detecting aspect of a power electronic circuit.
Owner:SOUTHEAST UNIV

Method for predicting faults of power electronic circuit based on FRM-RVM (fuzzy rough membership-relevant vector machine)

The invention discloses a method for predicting faults of a power electronic circuit based on an FRM-RVM (fuzzy rough membership-relevant vector machine), and the method comprises the following steps: monitoring voltage and current signals, and carrying out wavelet threshold denoising on the signals so as to form multidimensional circuit parameter vectors; carrying out dimensionality reduction on the multidimensional circuit parameter vectors so as to obtain multidimensional fault feature vectors; obtaining a fault feature vector sample set within a health tolerance range of the circuit; obtaining a fault feature vector of the circuit in the process of real-time operation at a periodic interval; computing the health degree of the fault feature vector to the fault feature vector sample set at each time point so as to form a health degree-time sequence of the circuit; giving out the threshold value of the health degree of the circuit; carrying out prediction on the health degree-time sequence of the circuit by using an RVM (Relevance Vector Machine) algorithm so as to obtain the health degree of the circuit in some future time, comparing the obtained health degree with the threshold value of the health degree, and determining the health situation of the circuit in some future time, thereby realizing the fault prediction of the circuit. By using the prediction method disclosed by the invention, the real-time state monitoring and health-status estimation on the power electronic circuit can be realized, thereby realizing the prediction on the future state of the circuit, and then predicting the time of fault occurrence in advance.
Owner:NANJING UNIV OF AERONAUTICS & ASTRONAUTICS

Device for monitoring state and diagnosing fault of power electronic circuit

The invention discloses a device for monitoring the state and diagnosing the fault of a power electronic circuit. The device has a structure that: a magnetic field detection module detects the magnetic field strength of the power electronic circuit, a signal conditioning module amplifies a voltage signal and an analog-to-digital conversion module performs analog-to-digital conversion; a fault diagnosis module comprises a time-domain and frequency-domain conversion module, a characteristic sort module and a comprehensive diagnosis module; the time-domain and frequency-domain conversion module is used for extracting the frequency characteristics of a time-domain waveform and supplies the frequency characteristics to characteristic sort sub-modules respectively; the characteristic sort sub-modules compare the received subsets to obtain partial diagnosis results corresponding to each characteristic subset and supply the results to the comprehensive diagnosis module; and the comprehensive diagnosis module synthesizes the partial diagnosis results of each characteristic subset to obtain a final diagnosis result. The device realizes the natural isolation of a detector from a main circuit; the different kinds of information carried by the magnetic field signal are treated respectively and then comprehensively judged, so the accuracy is higher; and the device can be applied to various power electronic circuits.
Owner:HUAZHONG UNIV OF SCI & TECH

A power electronic circuit fault diagnosis method based on an optimized deep belief network

The invention discloses a power electronic circuit fault diagnosis method based on an optimized deep belief network. The method comprises the following steps: (1) using an RT-LAB semi-physical simulation platform to set a fault expierment, and acquiring direct current side bus output voltage signals under different fault modes to serve as original fault characteristic quantities; (2) extracting anintrinsic mode function component and an envelope spectrum thereof of the output voltage signal by utilizing empirical mode decomposition, calculating a plurality of statistical characteristics, andconstructing an original fault characteristic set; (3) removing redundancy and interference features in the original fault feature set based on a feature selection method of an extreme learning machine, and performing normalization processing to serve as a fault sensitive feature set; (4) dividing the fault sensitive feature set into a training sample and a test sample, and preliminarily determining the structure of the deep belief network; (5) adopting a doodle search algorithm to optimize the deep belief network, and setting the number of hidden neurons of the network; And (5) obtaining a fault diagnosis result. According to the invention, the fault feature data size and the fault identification accuracy are improved.
Owner:WUHAN UNIV

Zero-current soft switching converter

ActiveCN103414340AEnhancement and effectSolve the problem that overload cannot realize soft switchingEfficient power electronics conversionDc-dc conversionCapacitanceSoft switching
The invention provides a zero-current soft switching converter and relates to the field of power electronic circuit topology design. The zero-current soft switching converter comprises a switching tube, a power diode, a voltage source inductor basic circuit and a current source inductor basic circuit, and further comprises a soft switching auxiliary unit. The soft switching auxiliary unit comprises a resonance inductor, a resonance capacitor and an auxiliary switching tube. The switching tube and the auxiliary switching tube are turn-off power switching devices provided with antiparallel diodes or having antiparallel diode characteristics. One end a of the resonance inductor is connected to a connection point of the switching tube and the power diode, and the other end b of the resonance inductor is connected to a current source inductor. The resonance capacitor and the auxiliary switching tube form a serial branch, one end of the serial branch is connected with an end b of the resonance inductor, and the other end c of the serial branch is connected to the negative pole N or the positive pole P or the middle point M of a voltage source. According to the zero-current soft switching converter, resonance current amplitude values of the soft switching converter can be automatically changed along with load current, therefore, loss of the soft switching converter can be further lowered, and efficiency can be further improved.
Owner:BEIJING JIAOTONG UNIV

IECMAC parameter identification-based power electronic circuit failure predicting method

The invention discloses an IECMAC parameter identification-based power electronic circuit failure predicting method, belonging to the technical field of power electronic failure test. The method comprises the following steps of: taking a set power device parameter value as an input training minimum neural network to obtain a failure sample set; judging the failure modal of an electronic circuit to be tested using information entropy-added detecting point electric signal training minimum neural network, and comparing the future time circuit performance parameter predicted by the SVR (support vector regression) with a circuit health threshold, to judge the failure modal of the electronic circuit to be tested; and predicting the real-time failure modal of the power electronic circuit to be tested by taking each detecting node electric signal which is timely monitored as an input repetition training minimum neural network. According to the method, a mathematical model of complex nonlinear system can not be built, and the generalization capability of an identifier can be further improved; and the regression can be carried out on the time sequence formed by system performance parameters by the SVR (support vector regression), the predicting precision and efficiency can be improved, and the on-line and real-time failure prediction can be realized.
Owner:NANJING UNIV OF AERONAUTICS & ASTRONAUTICS

Ensemble learning-based electric power electronic switch device network fault diagnosis method

An ensemble learning-based electric power electronic switch device network fault diagnosis method includes the following steps of: (1) collecting an output voltage or current signal vector set {Vn<q>}, n=1,2...N of an electric power electronic circuit in different switch device fault modes; (2) using principal component analysis to extract normalized fault characteristic vectors in the fault mode Fq from a signal vector Vn<q>, and obtaining a normalized fault characteristic vector set shown in the description according to the normalized fault characteristic vectors shown in the description; (3) using the normalized fault characteristic vector set shown in the description to train k neural network element classifiers in turn, and setting the number limitation K of the neural network element classifiers as 50 and a system error threshold e0; and (4) repeating steps (1) and (2) aiming at the circuits to be detected, obtaining a fault characteristic vector V* to be detected, enabling the fault characteristic vector to access the trained k neural network element classifiers, and using an ensemble learning method to obtain an ensemble recognition result. The ensemble learning-based electric power electronic switch device network fault diagnosis method can avoid defects of over learning of a single neural network and falling in local minimum, improves the classification precision of the neural network element classifiers.
Owner:HEFEI UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products