52results about How to "Strong noise suppression ability" patented technology

The invention discloses a resonant grounding power distribution network single-phase grounding fault line selection method and system. The method comprises the following steps: when a single-phase earth fault occurs in the power distribution network, acquiring real-time zero-sequence current data of each feeder line; and inputting the real-time zero-sequence current data into the fault line selection model to judge a fault line and output a result. The training process of the fault line selection model comprises the following steps: acquiring a noisy source domain data set from an electromagnetic transient simulation platform and a target domain data set from a real power distribution network; constructing a noise reduction automatic encoder as a feature extractor, and performing unsupervised pre-training by using the source domain data set to minimize a reconstruction error; pre-trained feature extractor parameters are frozen, and a trainable fault classifier is connected to form a transfer learning model; and carrying out supervised training on the model by using the source domain and target domain data sets and taking the fault line selection accuracy as a target to obtain a final model. By implementing the method provided by the invention, the accuracy and generalization ability of the line selection model in a real noise environment can be effectively improved through transfer learning and noise reduction feature extraction.

The invention discloses an effective signal extraction method and system based on CVAE, and relates to the field of digital signal processing, and the method comprises the specific steps: constructing a conditional variation auto-encoder which comprises an encoder, a re-parameterization module and a decoder; constructing a training data set based on the observation data set and the corresponding conditional variable set; training the conditional variation auto-encoder by using the training data set, and performing parameter optimization on the conditional variation auto-encoder by using a loss function based on physical consistency constraint; the loss function based on the physical consistency constraint comprises a reconstruction error item, a KL divergence loss item and a physical constraint loss item; acquiring to-be-processed data and corresponding conditional variables; and inputting to-be-processed data and conditional variables into the trained conditional variation auto-encoder to obtain effective signals. According to the method, physical consistency constraint is introduced through the conditional variation auto-encoder, high-frequency noise and pseudo-frequency components are effectively weakened, and a reconstructed signal is closer to a real signal.