3results about How to "Break out" patented technology

The application provides a provincial meteorological and administrative collaborative wind speed prediction method based on dynamic federal learning, relates to the cross technical field of artificial intelligence and energy meteorology, S1, basic data of N meteorological monitoring stations in a province is acquired, is divided into M initial subgraphs according to the administrative boundary of a prefecture-level city and is allocated an edge server, each collaborative subgraph pair is determined according to the Pearson correlation coefficient of the wind speed sequence of the station, the time sequence data deviation of the synchronized subgraph is synchronized through a dynamic time warping algorithm after every 3 rounds of federal iteration, and the subgraph data after synchronization is output. Through an endogenous decision and optimization framework, three links of dynamic coordination of cross-domain collaboration, local learning and gradient transmission are coordinated, and finally a global optimal provincial meteorological and administrative collaborative wind speed prediction method based on dynamic federal learning is achieved among multiple targets such as prediction accuracy, convergence speed and communication cost.

This invention provides a sub-meter-level distributed dual-parameter synchronous sensing system using a hybrid grating array, belonging to the field of fiber optic sensing. It includes: a positive and negative sideband modulation unit for generating linearly swept-frequency probe light with positive and negative sidebands; a tunable chaotic light source unit for generating wavelength-tunable low-coherence chaotic light and modulating it into chaotic light differential pulse pairs with different pulse width differences; a hybrid grating array comprising a series-connected array of identical chirped weak gratings (CFBG) and identical narrowband weak gratings (NFBG); the two beams are amplified and then combined and injected into the hybrid grating array; the CFBG array reflects the linearly swept-frequency probe light in response to vibration; the NFBG array reflects the chaotic light differential pulse pairs in response to temperature; the CFBG and NFBG arrays are completely separated in wavelength division multiplexing. This invention enables sub-meter-level spatial resolution dual-parameter synchronous measurement in a dense grating array without increasing the high-frequency hardware bandwidth.

This invention relates to a highly efficient underwater gravity field information measurement method based on swarm collaboration. It utilizes an unmanned swarm of underwater unmanned vehicles (UUVs) equipped with underwater gravimeters to simultaneously measure gravity information along multiple underwater survey lines. Using a surface vessel as a reference gravimeter, the underwater gravimeter is compared with the reference gravimeter before release and after retrieval to ensure consistency of underwater gravimeter measurement information. After release, the UUV navigates to the starting point of the survey line and, guided by a surface vessel, uses two-stage motion control to maintain the survey line's navigation and formation. Ultra-short baseline positioning and relative ranging are used to determine the UUV's precise position and velocity, enabling accurate compensation and correction of gravity measurements, acquisition of gravity anomaly information along the survey line, and construction of a gravity map. This invention achieves highly efficient underwater gravity measurement and rapid gravity map construction, improving measurement efficiency several times compared to traditional ship-based gravity measurement methods.