3 results about "Weighted least squares estimation" patented technology

This invention discloses a PID control method and related apparatus based on topology data analysis, belonging to the field of PID control technology. The method includes: mapping the time series of feedback signals representing the output state of the controlled object in a closed-loop control system into a two-dimensional point cloud; extracting the topological complexity features of the point cloud; generating fitting weights for each point cloud data point; constructing a weighted least squares estimator to extract the differential estimate of the two-dimensional point cloud; and replacing the differential term in the traditional PID controller with the differential estimate. Through point cloud mapping and weighted fitting, noise points can be suppressed, high-frequency noise amplification can be avoided, and inherent signal jitter can be suppressed. Dynamically adjusting the weights using topological features overcomes the defect that fixed differential gain cannot respond to signal changes. The adaptive weight adjustment mechanism of this invention can balance noise suppression and response speed without relying on a large fixed smoothing window, thus avoiding the introduction of large phase lag.

This invention discloses a data processing method and system for time-series synthetic aperture radar interferometry (InSAR), comprising: performing differential interferometry processing on N SAR images to obtain M interferograms and P highly coherent points; correcting the terrain residual phase, orbital error, and vertical atmospheric phase at the highly coherent points using a function model; and re-establishing a function model between the corrected phase and surface deformation. The core innovation lies in the fact that this invention deeply considers and establishes the variance and covariance matrices of turbulent atmospheric noise and decoherent noise in the spatiotemporal domain, thereby constructing a stochastic model that accurately characterizes the spatiotemporal correlation of noise. Based on this stochastic model, weighted least squares estimation is used to inversely derive the time-series surface deformation results and their uncertainties. This invention aims to improve the accuracy and reliability of time-series InSAR deformation monitoring by refining the modeling of the noise characteristics of the interferometric phase.

The application discloses a power grid monitoring and risk early warning method and system based on digital twinning and AI, which comprises the following steps: comparing, under the same time slice, the synchronous acquisition data with the nodal and branch flow calculation results and reference quantities of the digital twinning power grid model, and generating a residual vector; constructing an influence relationship matrix based on the power flow Jacobian matrix, the branch power balance relationship and the upstream and downstream power conservation relationship; solving each cause group disturbance variable by using weighted least squares estimation and sparse group constraint, and determining the confidence; correcting the digital twinning power grid model according to the confidence, updating the data reliability and labeling the historical acquisition samples; training the load prediction model based on the labeled samples, generating representative working conditions, performing power flow calculation, counting the out-of-limit conditions and obtaining the risk ranking. The application can improve the accuracy of power grid anomaly attribution, load prediction and risk early warning.