Abstract: The invention provides to a method and a system for fault diagnosis of a gearbox of a wind turbine generator based on stacked denoising autoencoders and relates to fault diagnosis. Signals obtained by pre-processing original vibration signals collected when the gearbox of the wind turbine generator is in different working states are used as training data. The training data are input into stacked denoising autoencoders. Meanwhile, a quantum-behaved particle swarm optimization algorithm is introduced to optimize the structure and parameters. Then, pre-processed test signals are input into the stacked denoising autoencoders that are trained to extract high-dimensionality fault features contained in the original vibration signals. Then, the extracted fault features are input into a least squares support vector machine to complete the fault diagnosis of the gearbox.

Abstract: The disclosure discloses an analog circuit fault feature extraction method and system based on an optimal wavelet basis function, and belongs to the field of electronic circuit engineering and computer vision, and the method comprises the steps of obtaining output signals of an analog circuit during different faults; sequentially applying wavelet transformation methods based on different wavelet basis functions to extract features of output signals; for each feature, calculating the center position of each fault, the distance from each fault data point to the center position, the farthest position of the fault data point and the average position of the fault data points; and determining an optimal wavelet basis function for analog circuit fault feature extraction according to a score discriminating method.

Abstract: A wireless channel monitoring and simulation device with multi-input multi-output (MIMO) is provided, which includes: a wireless channel monitor, configured to collect characteristic parameters of wireless channels in typical environments, and establish models based on the characteristic parameters; a model database, configured to store the characteristic parameter models and parameterize; an original signal, configured to input N different original signals; a wireless channel simulator, configured to simulate a typical channel environment according to the model database configuration, so that the original signal is the same as that in a real typical channel environment, and adopts a N-path output; an N-channel oscilloscope, configured to observe specific waveforms of N-path simulated signals; and a master computer software, configured to process, analyze, and store N-path output signals.

Abstract: A transformer failure diagnosis method and system based on an integrated deep belief network are provided. The disclosure relates to the fields of electronic circuit engineering and computer vision. The method includes the following: obtaining a plurality of vibration signals of transformers of various types exhibiting different failure types, retrieving a feature of each of the vibration signals, and establishing training data through the retrieved features; training a plurality of deep belief networks exhibiting different learning rates through the training data and obtaining a failure diagnosis correct rate of each of the deep belief networks; and keeping target deep belief networks corresponding to the failure diagnosis correct rates that satisfy requirements, building an integrated deep belief network through each of the target deep belief networks, and performing a failure diagnosis on the transformers through the integrated deep belief network.

Abstract: A transformer failure identification and location diagnosis method based on a multi-stage transfer learning theory is provided. Simulation is set up first, a winding parameter of a transformer to be tested is calculated, and a winding equivalent circuit is accordingly built. Different failures are configured for the equivalent circuit, and simulation is performed to obtain a large number of sample data sets. A sweep frequency response test is performed on the transformer to be tested, and detection data sets are obtained. Initial network training is performed on simulation data sets by using the transfer learning method, and the detection data sets are further trained accordingly. A failure support matrix obtained through diagnosis is finally fused. The multi-stage transfer learning theory is provided by the disclosure.

Abstract: A channel prediction system and a channel prediction method for an OFDM wireless communication system include a standard echo state network and a two-layer adaptive elastic network. In the method, with respect to each subcarrier of a pilot OFDM symbol, an echo state network is trained by using frequency domain channel information of each subcarrier obtained by channel estimation. The trained echo state network may realize short-term prediction of the frequency domain channel information. To overcome a likely ill-conditioned solution of an output weight in an echo state network, the output weight in the echo state network is estimated by using a two-layer adaptive elastic network.

Abstract: A wireless channel monitoring and simulation device with multi-input multi-output (MIMO) is provided, which includes: a wireless channel monitor, configured to collect characteristic parameters of wireless channels in typical environments, and establish models based on the characteristic parameters; a model database, configured to store the characteristic parameter models and parameterize; an original signal, configured to input N different original signals; a wireless channel simulator, configured to simulate a typical channel environment according to the model database configuration, so that the original signal is the same as that in a real typical channel environment, and adopts a N-path output; an N-channel oscilloscope, configured to observe specific waveforms of N-path simulated signals; and a master computer software, configured to process, analyze, and store N-path output signals.

Abstract: A method for vehicle-loading warehousing asset management based on an ultra-high frequency (UHF) radio frequency identification (RFID) path loss model, which includes the following steps. An electromagnetic wave is emitted by a tag reader. The electromagnetic wave is diffracted, reflected, and scattered when passing through a warehousing vehicle hood, and the electromagnetic wave is emitted and scattered through the ground. A UHF RFID tag attached to a front surface location region of assets receives electromagnetic waves of various paths emitted by the tag reader. The tag reader reads UHF RFID tag information. A transfer function of a tag receiving signal is constructed according to the tag information, and a path loss function during a UHF RFID tag sensing electromagnetic wave process is constructed according to the transfer function. The path loss is calculated according to the constructed path loss function. A location of the UHF RFID tag is obtained.

Abstract: An analog circuit fault feature extraction method based on a parameter random distribution neighbor embedding winner-take-all method, comprising the following steps: (1) collecting a time-domain response signal of an analog circuit under test, wherein the input of the analog circuit under test is excited by using a pulse signal, a voltage signal is sampled at an output end, and the collected time-domain response signal is an output voltage signal of the analog circuit; (2) applying a discrete wavelet packet transform for the collected time-domain response signal to acquire each wavelet node signal; (3) calculating energy values and kurtosis values of the acquired wavelet node signals to form an initial fault feature data set of the analog circuit; and (4) analyzing the initial fault feature data by the parameter random distribution neighbor embedding winner-take-all method, to acquire optimum low-dimensional feature data.

Abstract: A power electronic circuit troubleshoot method based on a beetle antennae optimized deep belief network algorithm including the following steps is provided. Output current signals of DC bus of a three-phase PWM rectifier under different switching device open circuit failure modes are collected as an original data set. Intrinsic mode function components of the output current signals under different switching device open circuit failure modes are extracted using empirical mode decomposition to construct an original failure feature set. Fault feature is selected based on extra-trees to generate final fault dataset. A structure of a deep belief network is optimized using a beetle antennae algorithm. An optimized deep belief network is trained using a training set and an obtained failure recognition result is verified using a testing set.

Abstract: The disclosure discloses a transformer DGA data prediction method based on multi-dimensional time sequence frame convolution LSTM, including the steps: firstly, collecting and dividing monitoring information of dissolved gas in transformer substation oil into a test set and a verification set; secondly, extracting characteristic parameters by adopting a non-coding ratio method, deleting data which are basically kept unchanged, and performing normalization, noise superposition etc.

Abstract: The disclosure discloses a power transformer winding fault positioning method based on deep convolutional neural network integrated with visual identification, including 1) a winding equivalent circuit is established, and a transfer function thereof is calculated; 2) a sine wave excitation source is set at one end of the power transformer winding to obtain the amplitude-frequency characteristic curve of each winding node; 3) circuits under various fault statuses are subjected to scanning frequency response analysis to extract amplitude-frequency characteristics; 4) a feature matrix is established based on the obtained amplitude-frequency characteristics; 5) scanning frequency response analysis is performed on the diagnosed power transformer to form a feature matrix; 6) the feature matrix is converted into an image, simulation and historical detection data are used as a training set, and a deep convolutional neural network is input for training; 7) diagnosed transformer is subjected to fault classification and

Abstract: An intermediate relay maloperation preventing device and method based on an improved recursive wavelet algorithm is provided. The device includes a power supply module, a voltage sampling circuit, an analog-to-digital conversion module, a DSP chip, and a relay maloperation signal shielding module. The voltage sampling circuit is connected to the analog-to-digital conversion module. The analog-to-digital conversion module is connected to the DSP chip. The DSP chip is connected to and controls a relay signal control module. The voltage sampling circuit collects a voltage. An improved recursive wavelet is used to extract a voltage feature. As such, identification of a fault signal and a normal signal is achieved, and real-time fault monitoring is accomplished. The detection method may be easily implemented, exhibits good filtering performance and anti-interference capability, delivers high detection accuracy, and may accomplish real-time online monitoring of intermediate relay faults.

Abstract: The disclosure provides an internal thermal fault diagnosing method for an oil-immersed transformer based on DCNN and image segmentation, including: 1) dividing an internal area of a transformer, and using fault areas and normal status as labels of DCNN; 2) through lattice Boltzmann simulation, randomly obtaining multiple feature images of the internal temperature field distribution of the transformer under normal and various fault state modes, and the fault area serves as a label to form the underlying training sample set; 3) obtaining historical monitoring information of the infrared camera or temperature sensor, and forming its corresponding fault diagnosis results into labels; 4) combining all monitoring information contained in each sample into one image, and then extracting the same monitoring information from the samples in the sample set to form a new image; 5) segmenting image sample and then inputting the same into DCNN for training to obtain diagnosis results.

Abstract: The disclosure discloses a fault locating method based on a multi-layer evaluation model. Firstly, determine a fault type to be inspected and a fault symptom which able to accurately and effectively reflect a power transformer operation status and determine a weight of each fault type by using an association rule and a set pair analysis. Then, establish a DBN model to perform feature extraction and classification on multi-dimensional data of a fault. Finally, perform a comprehensive evaluation on an existing diagnosis result by using the D-S evidence theory. Accordingly, the supporting strength of the common target is reinforced, while the influence of divergent targets is reduced. As a result, the uncertainty in the diagnosis result is significantly reduced. The disclosure is mainly used to monitor and diagnose a status variable of the power transformer in a real-time manner, and treats power transformer status evaluation as a multi-property decision issue.

Abstract: A nonlinear model transformation solving and optimization method for partial discharge positioning based on multi-ultrasonic sensor includes the following steps: (1) constructing a spatial rectangular coordinate system in a transformer, and setting a position of each ultrasonic sensor; (2) constructing a positioning model on the basis of an arrival time positioning method to obtain a nonlinear positioning equation set for solving a position of a PD source; (3) eliminating second-order terms in the nonlinear positioning equation set to transform the nonlinear positioning equation set into a linear equation set; (4) obtaining multiple sample initial values of a coordinate of the PD source; (5) screening the multiple sample initial values; (6) performing clustering processing on the multiple effective sample initial values by adopting an improved K-means algorithm; and (7) selecting a class with most cluster elements, and calculating a mean of the elements of the class to finally determine an optimal coordinate

Abstract: A serial IGBT voltage equalization method and system based on an auxiliary voltage source is disclosed. The method includes the following steps. (1) Detect a port dynamic voltage of each serial IGBT. (2) Perform dynamic overvoltage diagnosis respectively on the port dynamic voltage of each IGBT. (3) Supply emergency high level signal to the gate of the IGBT when there is dynamic overvoltage. (4) Stop supplying emergency high level signal to the gate of the IGBT, supply a constant voltage at the gate of the IGBT through the auxiliary voltage source. The invention provides a constant voltage through the auxiliary voltage source, prolongs the off time of the faulty IGBT, and turns off other IGBTs simultaneously, thereby achieving the purpose of serial IGBT voltage equalization.

Abstract: A method for diagnosing analog circuit fault based on cross wavelet features includes steps of: inputting an excitation signal to an analog circuit under test, and collecting time domain response output signals to form an original data sample set; dividing the original data sample set into a training sample set and a test sample set; performing cross wavelet decomposition on both sets; applying bidirectional two-dimensional linear discriminant analysis to process the wavelet cross spectra of the training sample set and the test sample set, and extracting fault feature vectors of the training sample set and the test sample set; submitting the fault feature vectors of the training sample set to a support vector machine for training an SVM classifier, constructing a support vector machine fault diagnosis model; and inputting the fault feature vectors of the test sample set into the model to perform fault classification.

Abstract: A power electronic circuit fault diagnosis method based on Extremely randomized trees (ET) and Stack Sparse auto-encoder (SSAE) algorithm includes the following. First, collect the fault signal and extract fault features. Then, reduce the dimensionality of fault features by calculating the importance value of all features using ET algorithm. A proportion of the features to be eliminated is determined, and a new feature set is obtained according the value of importance. Further extraction of fault features is carried by using SSAE algorithm, and hidden layer features of the last sparse auto-encoder are obtained as fault features after dimensionality reduction. Finally, the fault samples in a training set and a test set are input to the classifier for training to obtain a trained classifier. And mode identification, wherein the fault of the power electronic circuit is identified and located by the training classifier.

Abstract: A method includes steps: 1) obtaining monitoring information of different monitoring points in normal state of power equipment; 2) setting faults and obtaining monitoring information of different fault types, positions, monitoring points of the equipment; 3) taking the monitoring information obtained in steps 1) to 2) as training dataset, taking the fault types and positions as labels, inputting the training dataset and the labels to deep CNN for training; 4) collecting monitoring data, performing verification and classification using step 3), obtaining probability values corresponding to each of the labels; 5) taking classification results of different labels as basic probability assignment values, with respect to a monitoring system composed of multiple sensors, taking different sensors as different evidences for decision fusion, performing fusion processing using the DS evidence theory to obtain fault diagnosis result.