4 results about "Recurrence plot" patented technology

A structure estimation method (S1) comprising: a step (S12) for generating a recurrence plot from information about the structures of spatially adjacent moieties of a molecule by representing the primary sequence of the molecule on the time axis; a step (S13) for generating a distance matrix that provides the distance between any two vertices of the recurrence plot; a step (S14) for reconstructing time-series data by using multidimensional scaling with respect to the distance matrix; and a step (S15) for reconstructing the three-dimensional structure of the molecule from the reconstructed time-series data, wherein the distance matrix has, as a component, a post-transformation distance obtained by transforming a Jaccard distance related to the recurrence plot, and the post-transformation distance is obtained as a solution or an approximate solution of an equation in which said post-transformation distance is defined as a variable.

The invention discloses an on-line test method and system based on an electronic tag, particularly relates to the technical field of product identification analysis, and is used for solving the problem of space-time dislocation between an electronic tag reading event and a test data acquisition event caused by movement of a tested object in a continuous movement conveying scene. Motion state information of a measured object is acquired in real time, phase-space reconstruction is performed on the measured object, recurrence plot quantitative characteristics are calculated to evaluate a deterministic chaotic disturbance level, accordingly, a dominant oscillation mode is extracted, and an instantaneous phase of the mode at a label reading and data acquisition event moment is acquired; a phase-locked loop is configured by using a chaotic disturbance level, whether a phase locking state is reached is judged by analyzing phase difference evolution between two phases, and when the phase locking state is reached, a tag identifier is analyzed to call and execute a corresponding test program. And collecting test data, calculating an actual physical point location associated with the data based on the motion state information and the event moment, and finally generating a test data file.

This invention discloses a method and system for high-frequency transformer fault identification, belonging to the field of high-frequency transformer fault detection technology. The method comprises: acquiring a characteristic gas vector sequence of the high-frequency transformer and converting the characteristic gas vector sequence into an actual fault recurrence graph; generating an expanded dataset based on the actual fault recurrence graph, a pre-acquired random noise vector, and a preset initial depth convolutional generative adversarial network model; training a preset initial MobileNetV3 model based on the expanded dataset and the characteristic gas vector sequence and constructing a cross-entropy loss function, then updating the model with the goal of minimizing the cross-entropy loss function until a preset convergence condition is met, thus obtaining the MobileNetV3 model; inputting the fault recurrence graph to be tested into the MobileNetV3 model to obtain the fault detection result of the high-frequency transformer to be detected. Therefore, by implementing this invention, the low accuracy of high-frequency transformer fault identification and the insufficient ability to identify complex faults can be avoided, achieving high-precision and high-reliability identification of various types of high-frequency transformer faults.

The present invention improves the versatility of a feature amount in time series data. A feature amount extraction device (20) uses an inference model to extract a feature amount from a non-binary recurrence plot. In the non-binary recurrence plot, for each of all combinations of two samples selected from a plurality of samples included in the time-series data, a distance scale between the two samples is set to two-dimensional image information at positions determined by the order of one of the two samples and the order of the other in the time-series data. The inference model is constructed by machine learning which uses, as learning data, a non-binary recurrence plot generated from time-series data for learning.