公开(公告)号：US20210342502A1

公开(公告)日：2021-11-04

申请号：US16621233

申请日：2019-09-25

Applicant: Northeastern University

Inventor： Jian FENG ,  Chunyang YU ,  Senxiang LU ,  Chengze REN ,  Dazhong MA ,  Yunbo LI ,  Linping XU

IPC: G06F30/20 ,  H02J3/00

Abstract: A multiple objective optimization route selection method based on a step ring grid network for a power transmission line is configured to use multiple data for regional classification and to select virtual topological nodes to construct a virtual topology map. An overall route is planed according to the shortest and optimization route selection method. After selecting the virtual topology route, a semi annular domain of a step ring grid map is constructed through the connections of the topological nodes. After the segmentation of the semi-annular domain to form a plurality of grids, the grids are numbered. The grid attributes of the grids are used for optimizing the route. The multiple objective optimization function is constructed according to a distance function, a cost objective function and an angle cornering objective function, in order to collaboratively optimize the transmission line route.

公开(公告)号：US20180309294A1

公开(公告)日：2018-10-25

申请号：US15577127

申请日：2017-06-16

Applicant: Northeastern University

Inventor： Huaguang ZHANG ,  Jun YANG ,  Qiuye SUN ,  Feiye WU ,  Xinrui LIU ,  Dongsheng YANG ,  Zhiliang WANG ,  Jian FENG ,  Bonan HUANG ,  Yanhong LUO ,  Guotao HUI ,  Zhenwei LIU

IPC: H02J3/18 ,  H02J3/16 ,  G05F1/14

CPC classification number: H02J3/1885 ,  G05F1/14 ,  H02J3/16 ,  H02J3/18 ,  H02J3/1878 ,  H02J2003/007

Abstract: The invention provides a reactive power optimization system and a method of a power grid based on a double-fish-swarm algorithm. The system includes a power grid state data acquiring module, a reactive power regulating module and a reactive power executing module. The power grid state data acquiring module includes a power grid state data acquisitor and a relay transmitter. The reactive power regulating module is a control terminal. The reactive power executing module includes generator terminal voltage regulators, transformer tap regulators and reactive power compensation regulators. The method is used for acquiring the initial data to be optimized in the current network; and optimizing the initial data to be optimized in the current network based on a double-fish-swam algorithm so as to obtain optimal value of control variables in the power grid. According to the method, the distribution network to be optimized can realize reasonable reactive power flow distribution.

公开(公告)号：US20150308919A1

公开(公告)日：2015-10-29

申请号：US14692502

申请日：2015-04-21

Applicant: Northeastern University

Inventor： Huaguang ZHANG ,  Dazhong MA ,  Jian FENG ,  Jinhai LIU ,  Gang WANG ,  Zhenning WU ,  Qiuye SUN ,  Xiaoyu LI

IPC: G01M3/28

CPC classification number: G01M3/2807 ,  G01M3/243

Abstract: The present invention relates to an intelligent adaptive system and method for monitoring leakage of oil pipeline networks based on big data. The present invention effectively analyzes a large amount of data collected on site within a reasonable time period and obtains a state of a pipeline network by an intelligent adaptive method, thereby obtaining a topological structure of a pipeline network. The present invention specifically adopts a flow balance method in combination with information conformance theory to analyze whether the pipeline network has leakage; small amount of leakage and slow leakage can be perfectly and accurately alarmed upon detection; as a generalized regression neural network is adopted to locate a leakage of the pipeline network, an accuracy of a result is increased. Therefore, the present invention adopts a policy and intelligent adaptive method based on big data to solve problems of detecting and locating leakage of the pipeline network.

Abstract translation: 本发明涉及一种基于大数据监测油管网泄漏的智能自适应系统和方法。 本发明有效地分析了在合理时间段内现场收集的大量数据，并通过智能自适应方法获得了管网的状态，从而获得了管网的拓扑结构。 本发明具体采用流量平衡法与信息一致性理论相结合，分析管网是否有泄漏; 检测时可以完全准确地报警泄漏量低，泄漏量低; 采用广义回归神经网络来定位管网泄漏，提高了精度。 因此，本发明采用基于大数据的策略和智能自适应方法来解决检测和定位管网泄漏的问题。

公开(公告)号：US20230341354A1

公开(公告)日：2023-10-26

申请号：US18028010

申请日：2020-11-06

Applicant: Northeastern University

Inventor： Huaguang ZHANG ,  Jinhai LIU ,  Lei WANG ,  Jiayue SUN ,  Jian FENG ,  Gang WANG ,  Dazhong MA ,  Senxiang LU

IPC: G01N27/83 ,  G01B7/02

CPC classification number: G01N27/83 ,  G01B7/02

Abstract: Provided is an intelligent inversion method for pipeline defects based on heterogeneous field signals. The method includes the following steps: firstly, acquiring heterogeneous field signals, performing an abnormality judgement, then correcting base values of the heterogeneous field signals, and performing denoising treatment; padding the denoised heterogeneous field signals corresponding to the pipeline defects, unifying the heterogeneous field signals of different sizes into the heterogeneous field signals of same sizes, and performing a nonlinear transformation on signal amplitudes; designing a sparse autoencoder with an axisymmetric structure, and obtaining primary characteristics of the heterogeneous field signals; classifying the pipeline defects according to lengths, widths and depths to obtain category labels of the pipeline defects; designing a multi-classification neural network to classify the heterogeneous field signals, and extracting deep characteristics containing defect size information; and constructing a random forest regression model to realize intelligent inversion for sizes of the pipeline defects.

公开(公告)号：US20200210826A1

公开(公告)日：2020-07-02

申请号：US16345657

申请日：2019-02-13

Applicant: Northeastern University

Inventor： Jin hai LIU ,  Ming rui FU ,  Sen xiang LU ,  Hua guang ZHANG ,  Da zhong MA ,  Gang WANG ,  Jian FENG ,  Xin bo ZHANG ,  Ge YU ,  Hong qiu WEI

IPC: G06N3/08 ,  G06Q10/00 ,  G06N3/04 ,  G06N20/20 ,  G06N5/00 ,  G01N27/82

Abstract: Provided is an intelligent analysis system for inner detecting magnetic flux leakage (MFL) data in pipelines, including a complete data set building module, a discovery module, a quantization module and a solution module, wherein: a complete data set building method is adopted in the complete data set building module to obtain a complete magnetic flux leakage data set; a pipeline connecting component discovery method is adopted in the discovery module to obtain the precise position of a weld; an anomaly candidate region search and identification method is adopted in the discovery model to find out magnetic flux leakage signals with defects; a defect quantization method based on a random forest is adopted in the quantization module to obtain a defect size; and a pipeline solution based on an improved ASME B31G standard is adopted in the solution module to output an evaluation result.