Abstract: A method and a system for diagnosing a fault of a three-phase three-level rectifier are relate to the technical field of fault diagnosis of power electronic equipment, and provided to implement identification and location of an open-circuit fault of a power switching device thereof. A deviation between an expected value and an actual value of a phase-to-phase voltage is adopted as a diagnosis variable. The diagnosis variable is calculated by adopting a screening technique, thereby reducing calculation error to ensure accuracy of diagnosis. Only existing voltage current signals in a control system of the rectifier are required to calculate the diagnosis variable, so no additional hardware is required and low-cost fault diagnosis can be implemented. Different voltage thresholds are adopted for different fault characteristic sections, and the voltage thresholds are updated in real time according to a direct current side voltage, which improves diagnosis speed while ensuring higher robustness.

Abstract: A method and a system for power equipment diagnosis based on windowed feature and Hilbert visualization are provided, which belong to the field of power equipment fault diagnosis. The method includes: obtaining an original data set of monitoring data containing power equipment fault features; introducing windowed feature calculation considering logarithmic constraints to process data to obtain a feature sequence; using Hilbert visualization method for further processing to obtain a Hilbert image data set used to train and verify a convolutional neural network; and finally directly inputting newly obtained test sample data after windowed feature calculation and Hilbert visualization processing into the trained network for fault diagnosis and location.

Abstract: Provided are a failure diagnosis method and apparatus for open circuit failure of a power tube of a three-phase rectifier based on a current signal, relating to a failure diagnosis technique for power electronic equipment and capable of quickly and accurately diagnosing on an open circuit failure of the power tube of the three-phase rectifier without adding a hardware component. The failure diagnosis method only requires a sampled current existing in the control system of the rectifier and some intermediate computing signals and is therefore simple and requires little computing resource. A distorted current after the open circuit failure occurs in the power tube of the rectifier and a positive/negative half cycle where the current is present when the failure occurs serve as diagnostic variables. By analyzing the sampled current, a quick diagnosis on the power tube having the open circuit failure is provided. Thus, the invention is highly applicable.

Abstract: A method and a system for diagnosing a fault of a three-phase three-level rectifier are relate to the technical field of fault diagnosis of power electronic equipment, and provided to implement identification and location of an open-circuit fault of a power switching device thereof. A deviation between an expected value and an actual value of a phase-to-phase voltage is adopted as a diagnosis variable. The diagnosis variable is calculated by adopting a screening technique, thereby reducing calculation error to ensure accuracy of diagnosis. Only existing voltage current signals in a control system of the rectifier are required to calculate the diagnosis variable, so no additional hardware is required and low-cost fault diagnosis can be implemented. Different voltage thresholds are adopted for different fault characteristic sections, and the voltage thresholds are updated in real time according to a direct current side voltage, which improves diagnosis speed while ensuring higher robustness.

Abstract: A method and a system of identifying and estimating a complex analog circuit failure, belonging to the field of power electronic circuit failure prediction. The method includes the following steps: building a degradation simulation model of an analog circuit to be diagnosed, performing a parameter aging simulation experiment on different devices; extracting a time domain feature of each of output signals by using a time-series transformation method, building a health index of each of the devices based on angle similarity; identifying whether the analog circuit to be diagnosed is degraded and a starting point of degradation by combining a time moving window and a convolutional neural network; multiplexing part of hidden layers of the convolutional neural network and a long short term memory-recurrent neural network to estimate a health state of a degraded analog circuit; and evaluating prediction accuracy.

Abstract: Provided are a failure diagnosis method and apparatus for open circuit failure of a power tube of a three-phase rectifier based on a current signal, relating to a failure diagnosis technique for power electronic equipment and capable of quickly and accurately diagnosing on an open circuit failure of the power tube of the three-phase rectifier without adding a hardware component. The failure diagnosis method only requires a sampled current existing in the control system of the rectifier and some intermediate computing signals and is therefore simple and requires little computing resource. A distorted current after the open circuit failure occurs in the power tube of the rectifier and a positive/negative half cycle where the current is present when the failure occurs serve as diagnostic variables. By analyzing the sampled current, a quick diagnosis on the power tube having the open circuit failure is provided. Thus, the invention is highly applicable.

Abstract: A method and a system for power equipment diagnosis based on windowed feature and Hilbert visualization are provided, which belong to the field of power equipment fault diagnosis. The method includes: obtaining an original data set of monitoring data containing power equipment fault features; introducing windowed feature calculation considering logarithmic constraints to process data to obtain a feature sequence; using Hilbert visualization method for further processing to obtain a Hilbert image data set used to train and verify a convolutional neural network; and finally directly inputting newly obtained test sample data after windowed feature calculation and Hilbert visualization processing into the trained network for fault diagnosis and location.