9 results about "Earthquake warning system" patented technology

The application relates to the technical field of earthquake prediction, and particularly provides a lightweight on-site ground motion parameter prediction model construction method and an earthquake early warning system. The lightweight on-site ground motion parameter prediction model construction method comprises the following steps: training an initial prediction model according to acceleration waveform data when a P wave of an earthquake arrives, to obtain a pre-training prediction model; taking the pre-training prediction model as a teacher model, and transferring the knowledge of the teacher model to a student model through distillation; and constructing a lightweight on-site ground motion parameter prediction model based on the student model. The method can reduce the complexity and calculation amount of the student model by transferring the knowledge in the pre-training prediction model to the student model through distillation; and the lightweight on-site ground motion parameter prediction model can be constructed based on the student model, so that the demand of the model for hardware resources can be reduced while the on-site ground motion parameter prediction efficiency is ensured, and the deployable scene of the model is expanded.

This application relates to the field of offshore wind power safety monitoring technology, and discloses an earthquake early warning system based on the CZ1 Huaneng offshore wind power plant. The system includes dual-channel sensing units deployed at wind turbine nodes. Each sensing unit is configured to monitor T-wave disturbances in parallel through an active TDR detection channel and a passive harmonic sensing channel. A central early warning unit is configured to receive trigger signals and perform dual verification. First, the central early warning unit performs cross-channel coherence verification, requiring signals from the two channels from the same sensing unit to be triggered synchronously within a preset time window to filter out incoherent noise. Second, the central early warning unit performs array spatiotemporal coherence verification on verified credible events, fitting their spatiotemporal distribution to a wavefront propagation model to eliminate spatially incoherent local interference. This invention, through dual-channel orthogonal sensing and dual spatiotemporal coherence verification, eliminates interference at both the single-point and array levels, reduces the false alarm rate, and improves the reliability of early warning.

The invention provides a line earthquake early warning system evaluation parameter acquisition method and a related product, and relates to the technical field of earthquake early warning. The method comprises the following steps: according to an epicenter position parameter, a line position parameter and an S wave propagation rate, determining an influence starting moment and an influence ending moment of an earthquake S wave on a line and position mileage parameters of the line influenced at each moment between the influence starting moment and the influence ending moment; in a line mileage-time coordinate system, determining a first integral region of a position mileage parameter of an affected line from an influence starting moment to an influence ending moment, and a second integral region of a line early warning line section from an early warning moment to the influence ending moment; and determining early warning effect evaluation parameters of the line earthquake early warning system according to the overlapping proportion of the first integral region and the second integral region. According to the invention, comprehensive evaluation of the accuracy and timeliness of the line earthquake early warning system is realized.

The invention discloses an active triggering type cultural relic protection device and method based on pre-earthquake prediction, and belongs to the technical field of cultural relic protection. The device comprises a showcase body, and a carrying platform is arranged in an inner cavity of the showcase body; the carrying platform rapid evacuation device controls the carrying platform to execute an opening action according to a control instruction of the main control unit; the safe bearing unit is arranged in the protection area and used for bearing the falling cultural relics; the earthquake early warning receiving module receives and analyzes the earthquake motion parameters; the main control unit receives the seismic oscillation parameters, judges the damage level according to the seismic oscillation parameters and generates a control instruction; the state monitoring unit monitors the vibration state of the showcase body, the overturning angle of the carrying platform and the internal pressure of the inner-layer air bag assembly in real time. By integrating the earthquake early warning system, the rapid evacuation mechanism and the multi-stage composite buffering safety bearing unit, a full-chain protection strategy of pre-earthquake prediction, active triggering, lossless transfer and multi-stage energy absorption is achieved, and the survival rate and safety of cultural relics in a strong earthquake environment are remarkably improved.

The application relates to the technical field of earthquake early warning, and discloses an alarm method and a positioning system for abnormal real-time monitoring of an earthquake early warning station network, which comprises the following steps: obtaining M groups of original fluctuation signals based on M seat stations; extracting abnormal data of the original fluctuation signals, including data delay, server time service, network transmission flow and zero point drift; and triggering an alarm if the abnormal data is synchronously over-limit. The original fluctuation signals are obtained based on the M seat stations, four types of key abnormal data, including data delay, server time service, network transmission flow and zero point drift, are extracted, and alarm information is output when the abnormal data is synchronously over-limit, so that the abnormal conditions of the signal collection, transmission and processing links can be comprehensively covered, real-time capture of systematic signal abnormalities of the earthquake early warning system is realized, and the alarm can be triggered quickly.

The invention belongs to the field of seismic facies pickup, and discloses a seismic facies pickup method and system based on meta-knowledge memory bank enhancement, and the method comprises the steps: obtaining seismic waveform data; processing the seismic waveform data through a seismic phase pickup basic model encoder to obtain basic time sequence characteristics; generating an index through regional feature coding, and retrieving in a meta-knowledge memory library to obtain a memory vector; fusing the basic time sequence features and the memory vector by using a memory enhancement module to obtain enhanced feature representation; and decoding the enhanced feature representation by using a decoder to output P-wave and S-wave probability sequences, thereby completing a seismic phase pickup task. The method solves the problems that a traditional fine tuning method is forgotten and knowledge of similar areas cannot be reused, is especially suitable for continuous construction scenes of an earthquake monitoring network, can continuously accumulate and utilize knowledge along with continuous addition of new stations, and provides more and more intelligent earthquake phase pickup capacity for an earthquake early warning system.

The invention relates to the technical field of earthquake early warning, and discloses an earthquake early warning station network abnormity real-time monitoring alarm method and positioning system, and the method comprises the steps: obtaining M groups of original fluctuation signals based on M stations; extracting abnormal data of the original fluctuation signal, wherein the abnormal data comprises data delay, server time service, network transmission flow and zero drift; and if the synchronization of the abnormal data exceeds the limit, triggering an alarm. According to the method, original fluctuation signals are acquired based on M stations, four types of key abnormal data including data delay, server time service, network transmission flow and zero drift are extracted, and alarm information is output when the abnormal data synchronously exceed the limit, so that the abnormal conditions of signal acquisition, transmission and processing links can be comprehensively covered, and the reliability of the system is improved. Real-time capture of systematic signal abnormity of the earthquake early warning system is realized, and thus alarm is triggered rapidly.

The invention relates to an earthquake early warning system that provides an earthquake warnings to individuals, companies and public institutions through mobile applications or loT devices by instantly capturing the P wave of the earthquake by means of supplementary hardware, software and earthquake early detection stations equipped with velocity and accelerometers as well as a system that analyzes the said data. The relevant system consists of two modules: single and multi-array. Advantages achieved through this invention include low-cost network configuration, a linear seismic network with versatile detection capabilities, the use of artificial intelligence technology that eliminates false alarms, rapid system installation and deployment, and P-wave detection reduced to less than 1 second.

The invention discloses a simulation test and evaluation method and system for a high-speed railway earthquake early warning system, and the method and system are corresponding schemes, in the scheme, simulation test data can be automatically and efficiently generated, the defects of single, discrete and static data in the prior art are overcome, and abundant and realistic input sources are provided for the test of a tested system; moreover, the sending time sequence of test data can be accurately controlled, the real time-space characteristics of seismic wave propagation can be simulated, high-concurrency data generation is supported, and the performance and stability of the system during processing real-time, concurrency and interlaced information are checked; in addition, simulation data and a test result of a tested object can be automatically collected, and automatic analysis and calculation can be completed. Basic function verification can be completed, and key performance indexes of the system can be quantitatively and objectively measured and evaluated.