4 results about "Independent component analysis algorithm" patented technology

This invention relates to a method for separating vibration and flow noise in the underwater noise spectrum of a ship propeller, comprising: constructing a "frequency label" for vibration noise by fabricating two propeller models with identical geometry but significantly different material properties; a dual-model difference stage: calculating the absolute difference in the noise spectra of the two models and generating a vibration noise mask based on modal analysis results; a blind source separation stage: for the residual signal after difference, using an improved Independent Component Analysis (ICA) algorithm to further separate residual interference by utilizing the statistical independence of vibration noise; introducing a convolution kernel function in this stage to enhance the algorithm's adaptability to time-delayed signals; and introducing Cepstrum analysis technology to perform phase correction on the complex spectrum of the replacement frequency band. This method solves the significant shortcomings of existing noise control technologies in the coupling separation of vibration and flow noise, enabling the separation of the components of underwater noise from ship propellers, obtaining the noise components caused by blade vibration and the flow noise components separately.

This invention belongs to the field of geological disaster monitoring technology, specifically disclosing a method and system for quantitative inversion of ground fissures based on optical fiber and independent component analysis. The method includes: acquiring distributed optical fiber time-series strain monitoring data to construct an observation matrix; determining the number of components through principal component analysis; using spatial location as the observation dimension, employing independent component analysis to separate blind sources, extracting spatial independent components and corresponding time score matrices, thus decoupling the ground fissure signal from the background deformation signal; selecting components exhibiting continuous high amplitude as ground fissure strain anomaly components, and setting a threshold based on these components and the background noise level, defining intervals where the amplitude continuously exceeds the threshold as anomaly intervals; within these intervals, numerically integrating the anomaly components along the spatial direction to obtain the quantitative change in ground fissure width. This invention achieves automatic and accurate positioning of ground fissures and highly reliable quantitative inversion of their width under complex geological conditions.

This invention belongs to the field of data processing, specifically relating to a power metering method based on big data self-diagnosis. The invention discloses a power metering method based on big data self-diagnosis, which includes: real-time acquisition of multi-dimensional heterogeneous sensing data; training a dynamic floating baseline for metering using a spatiotemporal graph convolutional network; applying variational mode decomposition and independent component analysis algorithms to decouple the metering data stream into load characteristics, environmental disturbances, and hardware drift components; comparing the hardware drift components with the floating baseline in real time to calculate an error correction coefficient; and converting this coefficient into a digital compensation factor applied to the data processing module to achieve online correction of the metering results and synchronously generate a health diagnosis report. This invention, by constructing a dynamic baseline model and feature decoupling algorithms, achieves real-time self-detection of metering accuracy and digital closed-loop self-healing, eliminating external environmental interference and improving the robustness, management level, and operation and maintenance efficiency of the power metering system.

The application discloses a new energy power facility detection data management and analysis platform, comprising: a multi-source heterogeneous high-frequency synchronous induction system, each sensor node of which is equipped with a Beidou timing module, so that sampling error is controlled within 20ns by taking a second pulse as a sampling trigger source and adding a time stamp; an environment-driven dynamic reference flow form construction system for extracting low-dimensional embedding coordinates of environment characteristics through nonlinear flow form learning and constructing an ideal output hyper surface changing with the environment; and an endogenous performance deviation decoupling extraction system for calculating a residual matrix of real-time operation characteristics and ideal operation states and adopting an independent component analysis algorithm to decouple and extract an endogenous attenuation characteristic vector representing equipment intrinsic performance attenuation from the residual matrix. The application changes the monitoring reference from a fixed threshold to a dynamic baseline fluctuating with the environment, effectively separates environmental interference and equipment real performance attenuation, and improves diagnostic accuracy and preventive maintenance capability.