Abstract: A power transformer fault diagnosis method based on a stacked time series network, includes: collecting gas-in-oil data of a transformer in each substation; performing z-score normalization on the collected data to obtain a normalized matrix; dividing the normalized matrix into a training set and a test set in proportion; constructing a stacked time series network based on Xgboost and a bidirectional gated neural network, and inputting the training set and the test set to perform network training; and normalizing real-time collected data to obtain trainable data to predict a fault and update network parameters. The gas-in-oil data is predicted by using Xgboost and a gated neural network, obtains prediction data of a power transformer from two time series networks by using a meta learner, and obtains a fault diagnosis result of the transformer by using a Softmax layer. The neural network has accurate fault diagnosis performance and stable robustness.

Abstract: A DC/DC converter fault diagnosis method based on an improved sparrow search algorithm, includes: establishing an simulation module of the converter, selecting a leakage inductance current of a transformer as a diagnosis signal, and collecting diagnosis signal samples under OC faults of different power switching devices of the converter as a sample set; improving a global search ability of a sparrow search algorithm by using a Levy flight strategy; dividing the sample set into a training set and a test set, preliminarily establishing an architecture of a deep belief network, and initializing network parameters; optimizing a quantity of hidden-layer units of the deep belief network by using an improved sparrow search algorithm, to obtain a best quantity of hidden-layer units of the deep belief network; and training an optimized deep belief network obtained based on the improved sparrow search algorithm, and obtaining a fault diagnosis result based on a trained network.

Abstract: A DC/DC converter fault diagnosis method based on an improved sparrow search algorithm, includes: establishing an simulation module of the converter, selecting a leakage inductance current of a transformer as a diagnosis signal, and collecting diagnosis signal samples under OC faults of different power switching devices of the converter as a sample set; improving a global search ability of a sparrow search algorithm by using a Levy flight strategy; dividing the sample set into a training set and a test set, preliminarily establishing an architecture of a deep belief network, and initializing network parameters; optimizing a quantity of hidden-layer units of the deep belief network by using an improved sparrow search algorithm, to obtain a best quantity of hidden-layer units of the deep belief network; and training an optimized deep belief network obtained based on the improved sparrow search algorithm, and obtaining a fault diagnosis result based on a trained network.

Abstract: A transformer health state evaluation method based on a leaky-integrator echo state network includes the following steps: collecting monitoring information in each substation; performing data filtering, data cleaning and data normalization on the collected monitoring information to obtain an input matrix; inputting the input matrix into a leaky-integrator echo state network to generate trainable artificial data, and dividing the artificial data into a training set and a test set in proportion; constructing a deep residual neural network based on a squeeze-and-excitation network, and inputting the training set and the test set for network training; and performing health state evaluation and network weight update based on actual test data. Considering that a deep learning-based neural network needs a large amount of data, the present disclosure uses the leaky-integrator echo state network to generate the artificial training data.

Abstract: A method and a system for predicting remaining useful life of an analog circuit are provided. A simulation model of the analog circuit is built, and an output voltage is selected as a degradation variable. Different degradation cycles are set to extract degradation features of the output voltage. Key features that can reflect a degradation trend of a circuit component are selected. Multi-feature fusion and similarity model are adopted to construct a health indicator curve to characterize a degradation process of a full life cycle of different circuit components. A prediction model is established based on a temporal convolutional network and an attention mechanism, and preferably selected features and a constructed health indicator database are used as an input of a TCN-attention network to predict the remaining useful life of the circuit component.

Abstract: A method for diagnosing an open-circuit fault of a switching transistor of a single-phase half-bridge five-level inverter is provided. It includes the following steps. A semi-physical experiment platform with a DSP controller and an RT-LAB real-time simulator as its core constructed, and an output side voltage is selected as a fault signal variable. Empirical mode decomposition is used to extract a fault feature vector, and then a HHT time-frequency diagram of the fault feature vector is extracted, a voltage signal is converted into spectrum data, and time-frequency diagram fuzzy sets corresponding to different fault types are obtained. Fusion of the time-frequency diagram fuzzy sets of the same fault type is performed to obtain a fusion image that contains more fault features. The fusion images corresponding to all fault types are inputted into the deep convolutional neural network for training and testing, and a fault diagnosis result is obtained.