4results about How to "Improve decomposition accuracy" patented technology

The present invention discloses a non-intrusive load monitoring method and system based on SResNet-SCNN-BiLSTM network, which relates to the field of power load monitoring, including: selecting the load data of each electrical appliance from a household power consumption data set to obtain a total power sequence, and pre-processing the total power sequence to obtain an initial sample data set; using a CGAN network to expand the initial sample data set to obtain an expanded sample data set; combining an improved residual network and an SCNN-BiLSTM network to construct a load decomposition network model, and using the expanded sample data set for training; using the trained load decomposition network model to identify and decompose the total household power load to be identified, and obtain the loads of different electrical appliances. The present invention can effectively improve the accuracy of non-intrusive load monitoring in identifying power loads of different electrical equipment.

The invention relates to a cable temperature detection method, device and system and a storage medium, and relates to the technical field of cable detection. The method comprises the following steps: respectively injecting a plurality of groups of Gaussian white noise signals into an original temperature signal to obtain a plurality of groups of noise adding signals; according to the intrinsic mode function, performing signal decomposition operation and mean value processing operation on each group of noise adding signals to obtain an initial mode signal and an initial residual signal; performing signal decomposition operation on each group of Gaussian white noise signals by circularly adopting an intrinsic mode function, after multiple groups of noise decomposition signals are obtained each time, injecting each group of noise decomposition signals into a residual signal output last time, and performing signal decomposition operation and mean value processing operation on each group of noise adding residual signals to obtain a residual signal output last time; and obtaining a modal signal output at this time and a residual signal output at this time, and performing signal fusion on the multiple modal signals and the final residual signal to judge whether the target temperature signal is abnormal or not.

A non-intrusive multi-load load monitoring method and system based on shared time-series coding and load-specific refinement is disclosed, relating to the fields of smart grid, non-intrusive load monitoring, and energy data analysis. This method addresses the lack of existing non-intrusive multi-load load monitoring methods that can simultaneously address shared modeling, load difference representation, training stability, and engineering deployment feasibility. The process involves generating a fixed-length input window; after the input window is compressed to form latent space temporal features, multiple shared time-series coding modules extract the shared time-series representations for the corresponding multiple loads; these shared time-series representations are then fed into multiple independent load-specific refinement heads, which generate power predictions and state predictions for the target loads; residual gating is applied to the power predictions of the target loads using the state predictions, yielding the final decomposition results for the multiple target loads.

This invention belongs to the field of smart grid and load monitoring technology, and provides a multi-task non-intrusive load decomposition method system. The method includes: acquiring the total load data sequence at the input port of the power consumption unit, and inputting the total load data sequence in parallel to a power decomposition branch and a state identification branch; the power decomposition branch processes the total load data sequence to generate a power prediction value for the target appliance; the state identification branch processes the total load data sequence to generate an operating state probability for the target appliance; and the power prediction value and the operating state probability are fused to generate the final decomposed power of the target appliance. This invention, through a dual-branch multi-task architecture and output fusion mechanism, collaboratively optimizes the power prediction and state identification tasks, effectively solving problems such as insufficient long-term dependency modeling, inaccurate capture of diverse features, and power false alarms caused by inconsistent prediction results in existing technologies, significantly improving the accuracy and reliability of load decomposition.