公开(公告)号：US20230229172A1

公开(公告)日：2023-07-20

申请号：US18097833

申请日：2023-01-17

Applicant: BEIJING INSTITUTE OF TECHNOLOGY

Inventor： Bin XIN ,  Sai LU ,  Lihua DOU ,  Jie CHEN ,  Qing WANG ,  Miao WANG

IPC: G05D1/02 ,  G05B19/4155

CPC classification number: G05D1/0297 ,  G05B19/4155 ,  G05B2219/50391 ,  G05B2219/40078 ,  G05D2201/0216

Abstract: A multi-robot collaboration method in a flexible hardware production workshop is provided, by which allocation of workpiece machining tasks and transfer of workpieces in different workstations can be achieved and meanwhile relatively high calculation cost is avoided. According to the method, a distributed collaboration method is fully used, and in allusion to the current technical condition, the allocation of the workpiece machining tasks and the transfer of the workpieces in different workstations can be achieved and meanwhile the relatively high calculation cost is avoided. A multi-AGV path conflict eliminating method is used for avoiding possible collision of AGVs during movement. A centralized intervention and adjustment method is used for discovering and predicting system conflicts and failure problems and making timely dispatching and adjustment so as to improve the automation level and the flexibility level of a hardware workshop.

公开(公告)号：US20210135625A1

公开(公告)日：2021-05-06

申请号：US17093244

申请日：2020-11-09

Applicant: BEIJING INSTITUTE OF TECHNOLOGY

Inventor： Fang DENG ,  Zelang LIANG ,  Ning DING ,  Xinyu FAN ,  Xin GAO ,  Yuyun CAI ,  Jie CHEN

IPC: H02S50/10 ,  G06N3/08 ,  G06N3/04 ,  G06T7/00 ,  G06K9/62 ,  G06K9/46

Abstract: A photovoltaic array fault diagnosis method based on composite information is provided. The method includes: collecting and preprocessing composite information data of photovoltaic array working state, including image data and text data; using the image data of photovoltaic array working state to train a pre-established fault classification model of deep convolutional neural network, to thereby obtain an image fault classification model; using the text data of photovoltaic array working state to train a pre-established fault classification model based on a support vector machine, to thereby obtain a text fault classification model; fusing the image fault classification model and the text fault classification model by logistic regression algorithm to obtain a fusion model, and training the fusion model using the composite information data of photovoltaic array working state to thereby obtain the photovoltaic array fault diagnosis model.

公开(公告)号：US20240289610A1

公开(公告)日：2024-08-29

申请号：US18214881

申请日：2023-06-27

Applicant: Beijing Institute of Technology

Inventor： Gang WANG ,  Hongjie CAO ,  Jian SUN ,  Minggang GAN ,  Jie CHEN

IPC: G06N3/08 ,  G06F17/14 ,  G06F17/16 ,  G06N3/0442 ,  G06N3/0464 ,  H03H17/02

CPC classification number: G06N3/08 ,  G06F17/142 ,  G06F17/16 ,  G06N3/0442 ,  G06N3/0464 ,  H03H17/0257

Abstract: Disclosed is a hybrid data- and model-driven method for predicting remaining useful life of a mechanical component. The method of the present disclosure uses an extended Kalman filter to calibrate parameters of an exponential random model, automatically learns input embedded position information by means of an adaptive encoding layer of a hybrid driven prediction model, and then models a mapping relation between input data and the remaining useful life by means of a multi-head attention mechanism. The present disclosure retains both accuracy of a model-based method and a generalization capability of a data-driven method in combination with the calibrated exponential random model and a multi-head attention neural network structure, can improve accuracy of predicting the remaining useful life of the mechanical component, and has great significance for use of the hybrid data- and model-driven method in the field of intelligent manufacturing and health management of mechanical apparatuses.

公开(公告)号：US20240288855A1

公开(公告)日：2024-08-29

申请号：US18215266

申请日：2023-06-28

Applicant: Beijing Institute of Technology

Inventor： Jian SUN ,  Runqing WANG ,  Gang WANG ,  Minggang GAN ,  Jie CHEN

IPC: G05B19/418

CPC classification number: G05B19/41865 ,  G05B19/4183

Abstract: The present disclosure provides a flexible job-shop scheduling method and system and an electronic device. The method according to the present disclosure includes: randomly generating a plurality of flexible job-shop environments in a production job-shop according to a preset production target; constructing a scheduling strategy model of the production job-shop based on a Markov decision process; optimizing a feature extraction network, an actor network and a critic network simultaneously by using the scheduling strategy model and a plurality of data sets, and determining a scheduling plan corresponding to a maximum completion time as an optimal scheduling plan after the completion of the optimization; and completing the preset production target based on the optimal scheduling plan. According to the present disclosure, feature extraction is performed on the plurality of job-shop environments to generate a scheduling scheme, so as to improve the efficiency and rationality of flexible job-shop scheduling.

公开(公告)号：US20220115906A1

公开(公告)日：2022-04-14

申请号：US17485485

申请日：2021-09-26

Applicant: BEIJING INSTITUTE OF TECHNOLOGY

Inventor： Fang DENG ,  Yanxin JI ,  Xinyu FAN ,  Yeyun CAI ,  Chengwei MI ,  Feng GAO ,  Jie CHEN ,  Lihua DOU

IPC: H02J50/00 ,  H02J50/10 ,  H02J50/40 ,  H02J7/00 ,  H02J7/35 ,  G06F3/023 ,  G06F3/02

Abstract: A self-powered wireless keyboard by modifying the structure of a traditional membrane keyboard having a volcanic crater structure. Not damaging the original membrane keyboard structure, a micro magnet core is installed inside a cylindrical protrusion block under the key cap as a mover of the induction power generation device, and an induction coil is wound in a key slot of the keyboard base as the stator of the induction power generation device. In this way, when each key is pressed, it will produce induction current. A layer of flexible solar cell can be laid on the upper surface of the key, which can generate electricity by collecting the light energy in the surrounding environment during the time of daily illumination.

公开(公告)号：US20220147789A1

公开(公告)日：2022-05-12

申请号：US17468260

申请日：2021-09-07

Applicant: BEIJING INSTITUTE OF TECHNOLOGY

Inventor： Fang DENG ,  Yeyun CAI ,  Ning DING ,  Chengwei MI ,  Jiachen ZHAO ,  Xianghu YUE ,  Bin ZHANG ,  Chen CHEN ,  Wenjie CHEN ,  Jia ZHANG ,  Jie CHEN

IPC: G06M1/10 ,  H02J7/00

Abstract: A mechanical energy-based self-powering counting system is provided. The system includes an electromagnetic power generator, a count measuring circuit, a count energy supply circuit, a controller and a wireless transmission module. The electromagnetic power generator is driven by an external device and produces an electric signal and outputs the electric signal to the controller after passing it through the count measuring circuit. The controller processes the received signal, updates a count according to certain programming rules and sends data to the wireless transmission module. The energy from the electromagnetic power generator flowing through the count measuring circuit can supply power to the controller. An energy storage module in the count energy supply circuit performs voltage feedback on the controller. The controller monitors the voltage of the energy storage module to control whether it enters a charging state.