Method for acquiring water leakage amount of leakage area in water distribution system

    公开(公告)号:US11494853B2

    公开(公告)日:2022-11-08

    申请号:US16600551

    申请日:2019-10-13

    申请人: TONGJI UNIVERSITY

    摘要: The present invention relates to a method for acquiring the water leakage amount of a leakage area in a water distribution system. In the method, a hydraulic model is coupled with monitored data, and the water leakage amounts of different areas in the water distribution system are obtained through inversion by optimizing the spatial distribution of water leakage amounts. In addition to the coupling of the hydraulic model with the monitored data, virtual sectorization and pipe leakage risk assessment are used. By using a minimum difference between a simulated value and a monitored value at a pressure measurement point as a target, the water leakage amounts of different areas in the water distribution system are calculated by an optimization algorithm. Compared with the prior art, the present invention actualizes the effective identification of leakage areas in a water distribution system with a high leakage rate (i.e., with many leakage points).

    METHOD FOR ENHANCING METHANOGENESIS IN ANAEROBIC DIGESTION OF MUNICIPAL SLUDGE BY UTILIZING A FILTER SCREEN STRUCTURE

    公开(公告)号:US20220340467A1

    公开(公告)日:2022-10-27

    申请号:US17043518

    申请日:2019-12-10

    申请人: Tongji University

    IPC分类号: C02F11/04 B01D39/12 C02F11/12

    摘要: The disclosure relates to a method for enhancing methanogenesis in anaerobic digestion of municipal sludge by utilizing a filter screen structure, comprising: arranging a filter screen structure with titanium or titanium alloy as the framework and Fe3O4 as the coating in the anaerobic digestion system to accelerate the rate of hydrolysis and acidification, and increase the proportion of methane in biogas. Compared with the prior art, the disclosure increases the contact between Fe3O4 and anaerobic microorganisms by means of the screen structure; the stable crystal structure of Fe3O4 ensures the sustainability as an electron carrier while enriching electroactive microorganisms; titanium or titanium alloy, as a material with high strength, corrosion resistance, good biocompatibility, and good conductivity, can form a good match with Fe3O4 and assist in promoting the electron transfer; the disclosure has the advantages of low cost, high income, no need of repeated dosing and stable effect, and could strengthen the oxidation and decomposition of organic matter in the anaerobic digestion, accelerate the rate of methanogenesis, and increase the gas production.

    MULTI-SCALE DEEP SUPERVISION BASED REVERSE ATTENTION MODEL

    公开(公告)号:US20220292394A1

    公开(公告)日:2022-09-15

    申请号:US17401632

    申请日:2021-08-13

    申请人: Tongji university

    IPC分类号: G06N20/00 G06K9/62 G06K9/00

    摘要: A multi-scale deep supervision based reverse attention model is provided and includes an input end, a multi-scale feature learning module, an attention mechanism module, a reverse attention mechanism module, a deep supervision module, multiple loss functions, multiple average pool layers, multiple linear layers and multiple branches. The reverse attention mechanism module as provided can alleviate the problem of feature information loss caused by attention mechanisms, and part of the modules can be discarded in the testing phase, thereby improving the testing efficiency.

    WHOLE VEHICLE IN-LOOP TEST SYSTEM OF INTELLIGENT AUTOMOBILE

    公开(公告)号:US20220283056A1

    公开(公告)日:2022-09-08

    申请号:US17637802

    申请日:2020-09-28

    申请人: TONGJI UNIVERSITY

    IPC分类号: G01M17/007

    摘要: A whole vehicle in-loop test system of an intelligent automobile, including: a rotary drum platform, used for simulating a longitudinal movement of a test vehicle; an environment perception platform, disposed at a front end of the rotary drum platform, used for simulating a transverse movement of a test vehicle, and including a support base at a lower portion and a vehicle placing platform at an upper portion, where a transverse drive wheel is mounted at the lower portion of the support base, and the transverse drive wheel moves along a transverse track disposed on the ground; and a target vehicle simulation unit, disposed at a periphery of the environment perception platform, and configured to simulate a target vehicle.

    NEW INTERNET VIRTUAL DATA CENTER SYSTEM AND METHOD FOR CONSTRUCTING THE SAME

    公开(公告)号:US20220215109A1

    公开(公告)日:2022-07-07

    申请号:US17437049

    申请日:2019-12-16

    申请人: TONGJI UNIVERSITY

    IPC分类号: G06F21/62

    摘要: The present disclosure provides a new Internet virtual data center system and a method for constructing the same. The new Internet virtual data center system includes: an Internet data explorer to sample and estimate Internet data to generate a data resource distribution map, the data resource distribution map reflects attribute information of Internet data; an Internet virtual resource library to store data resource distribution map and sample data collected by the Internet data explorer; a data resource distribution map management module to manage data resource distribution map; and a data resource guidance service module to generate and provide guidance service for data collection and mining of a data demander according to data resource distribution map. The present disclosure overcomes the blindness and disorder of the big data collection and development of the existing data centers, and avoids waste of resources and energy.

    CROSS-MODALITY PERSON RE-IDENTIFICATION METHOD BASED ON LOCAL INFORMATION LEARNING

    公开(公告)号:US20220180132A1

    公开(公告)日:2022-06-09

    申请号:US17411007

    申请日:2021-08-24

    申请人: TONGJI UNIVERSITY

    摘要: Disclosed is a cross-modality person re-identification method based on local information learning, the method comprising the following steps: acquiring a standard data set and performing data enhancement on the standard data set; dividing the enhanced standard data set into a training set and a test set; constructing a cross-modality person re-identification training network based on a dual-stream ResNet50 convolutional neural network architecture; inputting the training set into the cross-modality person re-identification training network to obtain a cross-modality person re-identification test network through training; randomly selecting an image to be queried from the test set, and inputting the image to be queried and a candidate database from the test set into the cross-modality person re-identification test network to obtain an identification accuracy value corresponding to the image to be queried.

    TRUSTWORTHY SEARCH METHOD FOR SEARCH ENGINE BASED ON KNOWLEDGE GRAPH

    公开(公告)号:US20220147581A1

    公开(公告)日:2022-05-12

    申请号:US17376097

    申请日:2021-07-14

    申请人: TONGJI UNIVERSITY

    IPC分类号: G06F16/953 G06N5/02 G06F17/18

    摘要: The present invention relates to a trustworthy search method for a search engine based on a knowledge graph, which includes: acquiring a search keyword input by a user to construct a keyword pool; selecting a keyword according to a keyword selection policy, and respectively inputting the keyword to a search engine in sequence for searching to obtain a result returned by the search engine; constructing a knowledge graph of a Web page in sequence; selecting a specific knowledge mode; matching the knowledge graph with an existing semantics reliable knowledge graph library, and then computing a content support degree of each Web page according to a matching result; sorting the search engine under the same keyword by using a content support degree expectation of the Web page; and completing trustworthy search of the search engine based on the knowledge graph.