公开(公告)号：US20160180188A1

公开(公告)日：2016-06-23

申请号：US14603282

申请日：2015-01-22

Applicant: Beijing University of Technology

Inventor： Lijuan Duan ,  Shuo Qiu ,  Wei Ma ,  Jun Miao ,  Jia Li

IPC: G06K9/46 ,  G06T7/00 ,  G06T5/10

CPC classification number: G06K9/4671 ,  G06K9/3233 ,  G06K9/4623 ,  G06T5/10 ,  G06T7/13 ,  G06T7/174 ,  G06T7/269 ,  G06T2207/10012 ,  G06T2207/10021 ,  G06T2207/20021

Abstract: The present invention discloses a method for detecting a salient region of a stereoscopic image, comprising: step 1) calculating flow information of each pixel separately with respect to a left-eye view and a right-eye view of the stereoscopic image; step 2) matching the flow information, to obtain a parallax map; step 3) selecting one of the left-eye view and the right-eye view, dividing it into T non-overlapping square image blocks; step 4) calculating a parallax effect value for each of the image blocks of the parallax map; step 5) for each of the image blocks of the selected one of the left-eye view and the right-eye view, calculating a central bias feature value and a spatial dissimilarity value, and multiplying the three values, to obtain a saliency value of the image block; and step 6) obtaining a saliency gray scale map of the stereoscopic image from saliency values of the image blocks. The present invention provides a method for extracting stereoscopic saliency based on parallax effects and spatial dissimilarity, acquiring depth information by utilizing parallax, and combining visual central bias feature and spatial dissimilarity to realize more accurate detection of a stereoscopic salient region.

公开(公告)号：US09178404B2

公开(公告)日：2015-11-03

申请号：US13670601

申请日：2012-11-07

Applicant: Beijing University of Technology

Inventor： Desheng Li ,  Xiao Du ,  Kai Zhang ,  Bingfeng Jiao

IPC: H02K9/19 ,  H02K21/12 ,  H02K49/04 ,  H02K1/20 ,  H02K7/20

CPC classification number: H02K21/12 ,  H02K1/20 ,  H02K7/20 ,  H02K9/19 ,  H02K49/043

Abstract: A liquid-cooled self-excited eddy current retarder having two salient poles is provided. The liquid-cooled self-excited eddy current retarder may comprise a retarder rotor, a retarder stator, a retarder coil, a retarder generator and a control module. The retarder rotor may be a jagged turntable, and an axial cross section of the jagged turntable may be in an inverted h shape. Each of the two salient poles may be located at a respective one of two axial ends of the jagged turntable. The retarder rotor may be connectable to a transmission shaft, and an inner circle of the retarder stator may be coaxial with an outer circle of the retarder rotor. The retarder coil may be an independent coil and disposed between the two salient poles of the retarder rotor. The retarder coil may be affixed to the retarder stator.

Abstract translation: 提供一种具有两个凸极的液冷式自激式涡流缓速器。 液冷自激涡流缓速器可以包括延迟器转子，延迟器定子，延迟线圈，延迟器发生器和控制模块。 延迟器转子可以是锯齿状转台，并且锯齿状转台的轴向横截面可以是倒H形。 两个凸极中的每一个可以位于锯齿状转台的两个轴向端部中的相应一个。 延迟器转子可以连接到传动轴，并且减速器定子的内圆可以与延迟器转子的外圆共轴。 延迟线圈可以是独立的线圈并且设置在延迟器转子的两个凸极之间。 缓速器线圈可以固定到延迟器定子。

公开(公告)号：US20150135791A1

公开(公告)日：2015-05-21

申请号：US14296244

申请日：2014-06-04

Applicant: BEIJING UNIVERSITY OF TECHNOLOGY

Inventor： LIN MA ,  HONG-LI SUO ,  YI-CHEN MENG ,  YA-RU LIANG ,  LI-JIA CHEN ,  YAN XU ,  HUI TIAN ,  YI WANG ,  MIN LIU

IPC: B21B1/02

CPC classification number: B21B1/02 ,  B21B3/00 ,  B21B2265/14 ,  C22C1/023 ,  H01L39/126 ,  H01L39/2454

Abstract: A method of rolling NiW alloy tapes for coated conductors belongs to the technical field of metal materials rolling. According to the method, a cylindrical NiW alloy ingot with a diameter not less than 10 mm is used to be rolled back and forth along the axial direction as a rolling direction, wherein the content of W is 5˜7 at. %, and the axis of this ingot is perpendicular to the plane where the axes of working rollers are located. During rolling process, the cross sectional area reduction of the ingot is retained at 5% per pass. When the total cross sectional area reduction of the ingot is larger than 98% and the thickness of the tape is down to 60˜100 μm, the rolling is stopped, and thus the NiW alloy tape is obtained. The method has the advantages that the negative influence generated when the NiW alloy tape is produced from a cuboid initial NiW alloy ingot can be reduced as much as possible, the yield of the NiW alloy tapes is increased, as well as relatively ideal effects can be obtained in terms of the surface biaxial texture, the length and the axial quality.

Abstract translation: 轧制NiW合金带涂层导体的方法属于轧制金属材料的技术领域。 根据该方法，使用直径不小于10mm的圆柱形NiW合金锭作为轧制方向沿着轴向方向前后滚动，其中W的含量为5〜7at。 ％，并且该锭的轴线垂直于工作辊的轴线所在的平面。 在轧制过程中，锭的横截面积减少量保持在每通过5％。 当锭的总横截面积减小大于98％并且带的厚度降至60〜100μm时，停止轧制，从而获得NiW合金带。 该方法的优点在于，可以尽可能地减少由长方体的初始NiW合金锭制造NiW合金带时产生的负面影响，NiW合金带的收率提高，相对理想的效果可以 从表面双轴纹理，长度和轴向质量方面获得。

公开(公告)号：US20250103051A1

公开(公告)日：2025-03-27

申请号：US18972786

申请日：2024-12-06

Applicant: BEIJING UNIVERSITY OF TECHNOLOGY

Inventor： Naigong Yu ,  Yishen Liao ,  Zongxia Wang ,  Hejie Yu ,  Jianjun Yu ,  Xudong Liu ,  Ruihua Wang

IPC: G05D1/243 ,  G05D1/222 ,  G05D101/15 ,  G05D105/80 ,  G06T7/70

Abstract: A method for constructing episodic memory model based on rat brain visual pathway and entorhinal-hippocampal structure mainly applied to environment cognition and navigation of an intelligent mobile robot to complete tasks of environment cognition map construction and target-oriented navigation is provided. The image information of the environment, the head-direction angle and speed of the robot are collected, and then the head-direction angle and speed of the robot are input into the entorhinal-hippocampal CA3 neural computational model to obtain the robot's precise position. The visual information is input into the computational model of the visual pathway to obtain the scene information in the current vision of the robot. The above two kinds of information are fused and stored in a cognitive node with the topological relationship. Utilizing scenario information to correct the path integration errors during the exploration process of the robot, thereby constructing the episodic cognitive map representing the environment.

公开(公告)号：US12228549B2

公开(公告)日：2025-02-18

申请号：US17966175

申请日：2022-10-14

Applicant: Beijing University of Technology

Inventor： Zenghua Liu ,  Wenshuo Jiang ,  Zhaojing Lu ,  Yanhong Guo

IPC: G01N29/24 ,  G01N29/04 ,  G01N33/2045

Abstract: An acoustic field diffusion type electromagnetic acoustic transducer with improved periodic permanent magnets is provided, which includes periodic permanent magnets, a transducer framework, improved racetrack shaped coils and a transducer connector.

公开(公告)号：US12187632B2

公开(公告)日：2025-01-07

申请号：US17766175

申请日：2021-10-29

Applicant: Beijing University of Technology

Inventor： Dan Cui ,  Chen Lu ,  Zi'en Tang

IPC: C02F3/00 ,  C02F3/28 ,  C02F101/16 ,  C02F101/30

Abstract: The disclosure discloses a method for enhancing denitrification of sewage with a low carbon-to-nitrogen ratio by using an electrode biocarrier, and relates to the field of sewage treatment. The disclosure uses a conductive material as a microbial carrier and a potentiostat to induce a micro-electric field for directional acclimation and enrichment of electroactive denitrification microorganisms, and realizes a high-efficiency denitrification of the sewage with a low carbon-to-nitrogen ratio. The disclosure aims to provide a technical method for solving the problem of deep denitrification of municipal sewage with a low carbon-to-nitrogen ratio.

公开(公告)号：US20240419872A1

公开(公告)日：2024-12-19

申请号：US18727294

申请日：2023-04-26

Applicant: Beijing University of Technology

Inventor： Jian TANG ,  Heng XIA ,  CanLin CUI ,  Junfei QIAO

IPC: G06F30/27 ,  G06F111/10

Abstract: The invention provides a soft measurement method for dioxin emission of grate furnace MSWI process based on simplified deep forest regression of residual fitting mechanism. The highly toxic pollutant dioxin (DXN) generated in the solid waste incineration process is a key environmental index which must be subjected to control. The rapid and accurate soft measurement of the DXN emission concentration is an urgent affair for reducing the emission control of the pollutants. The method comprises the following steps: firstly, carrying out feature selection on a high-dimensional process variable by adopting mutual information and significance test; then, constructing a simplified deep forest regression (SDFR) algorithm to learn a nonlinear relationship between the selected process variable and the DXN emission concentration; and finally, designing a gradient enhancement strategy based on a residual error fitting (REF) mechanism to improve the generalization performance of a layer-by-layer learning process. The method is superior to other methods in the aspects of prediction precision and time consumption.

公开(公告)号：US12119464B2

公开(公告)日：2024-10-15

申请号：US18507242

申请日：2023-11-13

Applicant: BEIJING UNIVERSITY OF TECHNOLOGY

Inventor： Dean Pan ,  Xiaoguang Zhang ,  Yifan Wang ,  Qijun Zhang ,  Wei Wang

IPC: H01M10/54 ,  C22B1/00 ,  C22B3/08 ,  C22B3/22 ,  C22B3/26 ,  C22B7/00 ,  C22B47/00

CPC classification number: H01M10/54 ,  C22B1/005 ,  C22B3/08 ,  C22B3/22 ,  C22B3/26 ,  C22B7/006 ,  C22B47/00

Abstract: The present invention provides a method for preferentially recovering manganese from waste lithium-rich manganese-based cathode material, the method comprising: step 1) calcination and leaching: mixing the waste lithium-rich manganese-based cathode material with ammonium sulfate and then performing low-temperature calcination, leaching the calcination product with water, and then performing solid-solution separation to obtain a leaching solution; step 2) complexing and manganese separating: adding ammonium sulfite to the leaching solution obtained in step 1) for a complex reaction to obtain manganese-rich residue; step 3) oxidation leaching: adding an oxidant to the manganese-rich residue obtained in step 2) to perform oxidation leaching, and adjusting the pH of the solution to obtain a manganese-rich solution; and step 4) extracting and stripping. The method realizes the preferential and productive recovering of manganese from waste lithium-rich manganese-based cathode materials, avoids the negative impact of polymetals in the conventional recovery process, and has economic and environmental benefits.

公开(公告)号：US12105075B2

公开(公告)日：2024-10-01

申请号：US17472433

申请日：2021-09-10

Applicant: BEIJING UNIVERSITY OF TECHNOLOGY

Inventor： Honggui Han ,  Chenxuan Sun ,  Junfei Qiao

IPC: G06N3/043 ,  C02F1/00 ,  G01N33/18 ,  G06N3/08

CPC classification number: G01N33/1806 ,  G06N3/043 ,  G06N3/08 ,  C02F1/008 ,  C02F2209/16

Abstract: A total nitrogen intelligent detection system based on multi-objective optimized fuzzy neural network belongs to both the field of environment engineer and control engineer. The total nitrogen in wastewater treatment process is an important index to measure the quality of effluent. However, it is extremely difficult to detect the total nitrogen concentration due to the long detection time and the low prediction accuracy in the wastewater treatment process. To solve the problem, multi-objective optimized fuzzy neural network with global optimization capability may be established to optimize the structure and parameters to solve the problem of the poor generalization ability of fuzzy neural network. The experimental results show that total nitrogen intelligent detection system can automatically collect the variables information of wastewater treatment process and predict total nitrogen concentration. Meanwhile, in this system, the detection method can improve the prediction accuracy, as well as ensure the total nitrogen concentration be obtained in real-time and low-cost.

公开(公告)号：US20240302341A1

公开(公告)日：2024-09-12

申请号：US18276179

申请日：2022-10-27

Applicant: BEIJING UNIVERSITY OF TECHNOLOGY

Inventor： Jian TANG ,  Heng XIA ,  Canlin CUI ,  Junfei QIAO

IPC: G01N33/00 ,  G06N20/20

CPC classification number: G01N33/0075 ,  G06N20/20

Abstract: A broad hybrid forest regression (BHFR)-based soft sensor method for DXN emission in a municipal solid waste incineration (MSWI) process, including: based on a broad learning system (BLS) framework, constructing a BHFR soft sensor model for small sample high-dimensional data by replacing a neuron with a non-differential base learner, where the BHFR soft sensor model includes a feature mapping layer, a latent feature extraction layer, a feature incremental layer and an incremental learning layer, and the method includes: mapping a high-dimensional feature; extracting a latent feature from a feature space of a fully connected hybrid matrix, and reducing model complexity and computation consumption based on an information measurement criterion; enhancing a feature representation capacity by training the feature incremental layer based on an extracted latent feature; and constructing the incremental learning layer based on an incremental learning strategy, obtaining a weight matrix with a Moore-Penrose pseudo-inverse, and implementing high-precision modeling.