Chinese Academy of Sciences

Huawei Technologies Co., Limited

Beijing University of Posts and Telecommunications

Yibo Wang

Yikang Zheng

Qingfeng Xue

Yi Zhi Yao

Shaojiang Wu

Huan Wang

Yong Zhao

Guoen Cao

Jianhong Guo

Xinke Huang

Zhe Wang

Pei Jian Liu

Hao Liang

Rui Cao

Xuechun Lin

Zhiyan Zhang

Weixia Zou

Wenhao Ma

Yi Yin Yao

Yannan Liu

Junlong Lu

Hongyang You

Xinlei Zhang

Zizhuo Ma

Embodiments of the present disclosure provide a multi-physical field imaging method based on PET-CT and DAS, comprising: wrapping distributed acoustic sensors on a surface of a non-metallic sample to be tested, and then placing them in a pressure device; loading triaxial pressures; preparing a tracer fluid; pumping the tracer fluid into the non-metallic sample; collecting PET images and CT images of internal structure of the non-metallic sample, meanwhile, monitoring internal acoustic emission events of the non-metallic sample in real time; combining the PET images with the CT images, to obtain PET/CT images; locating the acoustic emission events, and obtaining occurrence time and spatial location of internal structural perturbations; and analyzing a mechanism of fluid-solid coupling effect in the non-metallic sample under loaded stress. The imaging method and system of the present disclosure can accurately and reliably image the fluid-solid coupling process in the material.

Multi-physical field imaging method and system based on PET-CT and DAS

A seismometer with high sensitivity, broadband and all-dip is provided, The which relates to the technical field of seismometer, including a first force feedback module, an insulator, a top cover, a terminal post, an upper leaf spring, a mass block, a casing, a sealing ring, an insulation gasket, a guide spring, a wire frame, a magnetic shoe, a compensation ring, a lower leaf spring, a bottom cover, a second force feedback module and a third force feedback module. It provides the broadband seismometer technology based on dynamic force balance feedback and the all-dip broadband seismometer technology based on dip angle perception, which breaks through the limitations of conventional seismometers in sensitivity, frequency band, and dip angle, and truly realizes a seismometer with high sensitivity, broadband, and all-dip.

Seismometer with high sensitivity, broadband and all-dip

Embodiments of the present disclosure provide a DAS same-well monitoring real-time microseismic effective event identification method based on deep learning, including: constructing a DAS-based horizontal well microseismic monitoring system; constructing a training data set, including microseismic event data, pipe wave data and background noise data with different types of labels; constructing a signal identification module; training the signal identification module by using the training data set; preprocessing actual monitoring data, inputting the preprocessed data into the signal identification module to obtain an output result; marking microseismic events identified in the output result, and updating the marked microseismic events into the training data set; and adjusting and updating the signal identification module. The identification method according to the present disclosure can identify microseismic events in DAS same-well monitoring data in real time and efficiently.

DAS same-well monitoring real-time microseismic effective event identification method based on deep learning

Embodiments of the present disclosure provide a real-time microseismic magnitude calculation method based on deep learning and a corresponding device. The method includes: constructing a DAS-based horizontal well microseismic monitoring system; constructing a training data set; constructing a magnitude calculation module, wherein the magnitude calculation module comprises two input branches of frequency spectrum and time waveform, the two input branches use a 3-layer convolution structure to extract frequency characteristic and waveform characteristic of a microseismic event, and then a model fusion is performed, and then 2 fully connected layers are used, and finally a calculated magnitude is outputted; training the magnitude calculation module; and analyzing and processing field data. The microseismic magnitude calculation method in the present disclosure improves the ability to quickly estimate the microseismic magnitude, without the need for converting the strain data, and improves the accuracy of the microseismic magnitude estimation.

Real-time microseismic magnitude calculation method and device based on deep learning

The application discloses an AI real-time microseism monitoring node, which includes a processor and a data acquisition device, an AI calculation device, and a communication device connected to the processor, wherein the AI calculation device is provided with pre-trained microseism data analysis Device, and the processor is configured to perform the following operations: controlling the data acquisition equipment to acquire microseism data; turning on the AI calculation device to calculate the acquired microseism data by means of the microseism data analysis device to determine the valid event data associated with the microseism; and sending the valid event data to the remote data center through the communication device.

Artificial intelligence real-time microseism monitoring node

An artificial intelligence calculation method and apparatus for monitoring an earthquake in real time based on edge cloud cooperation is applied to a micro-earthquake data processing system. The micro-earthquake data processing system includes an edge calculation device and a remote server in communication connection with the edge calculation device. The remote server deploys a micro-earthquake data analyzing model based on an artificial intelligence to the edge calculation device in advance. The method includes steps of receiving, by the remote server, effective event data related to the micro-earthquake from the edge calculation device; performing a transfer training to the micro-earthquake data analyzing model by the remote server according to the effective event data; and updating the model after the micro-earthquake data analyzing model that has been transfer-trained is transmitted to the edge calculation device by the remote server.

Artificial intelligence calculation method and apparatus for monitoring earthquake in real time based on edge cloud cooperation, and storage medium

A laser cleaning system including a laser source, an energy-transferring optical fiber, a laser cleaning head, a coreless motor, a connection lens barrel, and a mirror.

Laser cleaning system

A high-voltage isolation withstand planar transformer and its high-voltage insulation method are provided. An insulating medium is provided between low-voltage windings and high-voltage windings. High-frequency current flows through the windings and generates a high-frequency alternating magnetic field to achieve isolated energy transmission. The low-voltage windings are connected to low-voltage side connection terminals, and the high-voltage windings are connected to high-voltage side connection terminals through a high-voltage winding leading-out foil. An annular hollow part of the low-voltage windings and the high-voltage windings is provided with a magnetic core. A stress grading method is provided to control the distribution of the electric field around the high-voltage winding leading-out foil. A voltage-balancing element group provides a voltage potential with a gradient change between the high-voltage winding leading-out foil and the low-voltage windings. The new transformer has small size, high power density and low cost.

High-voltage isolation withstand planar transformer and high-voltage insulation method thereof

This invention proposes a three-phase CLLC bidirectional DC-DC converter, which includes a high-voltage side voltage dividing capacitor module, a three-phase half-bridge series module, a three-phase half-bridge parallel module, a three-phase primary/secondary side resonant module, a three-phase isolation transformer and a low-voltage side capacitor module. The high-voltage side voltage dividing capacitor module includes three voltage dividing capacitors. The three-phase half-bridge series/parallel module includes three bridge arms connected in series/parallel. Each bridge arm includes two switches connected in series. The three-phase primary/secondary side resonant module includes a, b, c three-phase primary/secondary side resonant tank. The three-phase isolation transformer includes three single-phase transformers a, b, and c. The voltage of the high-voltage side is divided through the voltage dividing capacitors to reduce the voltage stress of the switches, and the switching loss is diminished via the high-frequency soft switching technology.

Three-phase CLLC bidirectional DC-DC converter and a method for controlling the same

A large-scale photovoltaic direct current (DC) series boost grid-connected system with a power balancer, including N photovoltaic DC converters and N&#x2212;1 power balancers, wherein N&#x2265;2. The output ends of the photovoltaic DC converters are connected successively in series and then connected to the DC grid, and the input ends of the photovoltaic DC converters are respectively connected to the output ends of the photovoltaic power generation unit. Among the photovoltaic DC converters, which are arranged successively in series, a power balancer is disposed between the input ends of two photovoltaic DC converters adjacent to each other. The N&#x2212;1 power balancers are arranged corresponding to the set N&#x2212;1 photovoltaic DC converters respectively to balance the input power of the corresponding photovoltaic DC converter, thereby eliminating a difference between the output voltages of the photovoltaic DC converters.

Large-scale photovoltaic DC series boost grid-connected system with power balancer

A series-type photovoltaic high-voltage direct current (DC) grid-connected converter topological circuit and a modulation method thereof, wherein the topological circuit includes a high-frequency transformer configured to isolate a primary side circuit from a secondary side circuit. The primary side circuit includes a high-frequency full-bridge inverter circuit, an active-clamping circuit, an input capacitor C, an input diode D, and a boost inductor Land adjusts the boost mode and buck mode of the topological circuit. The secondary side circuit includes a high-frequency rectifying circuit, a filter capacitor Cand a filter capacitor C, and rectifies and filters an output voltage of the high-frequency transformer. The secondary side circuit further includes a switch tube Q, and the switch tube Qadjusts the secondary side circuit into a voltage multiplication circuit to double the output voltage of the high-frequency transformer.

Series-type photovoltaic high-voltage DC grid-connected converter topological circuit and modulation method thereof

Embodiments of the present invention disclose a node scheduling method, where the method includes: configuring, for a node, a working period matched with a performance indicator of the node, where duration of the working period is an integer multiple of duration of a super frame, and the super frame is a super frame corresponding to a beacon frame in a network in which the node is located; and sending, to the node, an updated beacon frame that includes information about the working period, so that the node acquires the information about the working period from the updated beacon frame, receives a working beacon frame, establishes a super frame corresponding to the working beacon frame until the working period ends, and then repeats the receiving a working beacon frame and establishing a super frame corresponding to the working beacon frame until the updated beacon frame is received again.

Growing community of inventors

Beijing, China

Yibo Wang