Contemporary Amperex Technology Co., Ltd.

Contemporary Amperex Technology (Hong Kong) Limited

Shandong University

Contemporary Amperex Technology Co., Limted

Fujian University of Technology

Manteia Technologies Co., Ltd.

Fujian Special Equipment Inspection and Research Institute

Fuzhou Xinaotena Technology Co., Ltd

Fuzhou Ecloudia Information Technology Co., Ltd

Xiamen Meitu Technology Co., Ltd.

Contemporarv Amperex Technologv Co., Limited

Contemporary Amperex Technology Limited

Wei Zhang

Yizhen Hou

Zhimin Dan

Shichao Li

Yanhua Lu

Mingshu Du

Jia Xu

Shenzhi Tang

Jian Ruan

Teng Yu

Xiyang Zuo

Xingyuan Wu

Jiechao Luo

Wenbin Lu

Taosheng Zhu

Meng Li

Jinbo Cai

Zhanyu Sun

Guowei Li

Xiong Zheng

Weiping Sun

Yanru Li

Yu Yan

Xiao Wang

Yuqian Wen

Xinwei Chen

Chao Zeng

Guoliang Hu

Xiaowei Zhang

Chengyong Liu

Shengwu Zhang

Minghao Tang

Li Tan

Lidan Yan

Qiandeng Li

Zhanliang Li

Jinfeng Gao

Siying Huang

Baohai Du

Qidong Lou

Lina Zhu

Chao Chen

Yibin Li

Liansong Wang

Zhipeng Chen

Fupeng Cai

Ran Song

Zhiwen Wang

Qichao Zhou

Zhongnan Xu

Qinda Zeng

Jiapeng Sheng

Yanyun Chen

Wenhao Tan

Jiyu Cheng

Xiaolei Li

Benqing Lin

Xing Fang

Shuo Yang

Bofeng Liu

Xian Huang

Xiang Wu

Yiqun Huang

Weiqing Wu

Huixiu Luo

Longzhen Lin

Zhaocai Chen

Meilin Chen

Yao Lin

Youyi Ye

Jinghe Chen

Jinneng Liu

Shukeng Ye

Yong Yin

Qin Lin

Liwan Shi

Lingke Kong

Zuen He

Delong Shi

Jianpeng Deng

Yuehu Liu

Shilei Chu

Siwen Huang

Jinwei Lin

Dongfang Ding

Jian Zhang

Shuai Song

Songlin Fu

Caiyu Bao

Changding Zhang

Xiyang Zou

Linglong Tang

Feng Pan

A method for cooperating packing actions and unpacking actions of mechanical arm based on deep reinforcement learning (DRL), wherein a synergistic effect between a packing action and an unpacking action is learnt by means of a packing-unpacking network (PUN), thereby improving the packing precision and efficiency; and a packing heuristic algorithm and an unpacking heuristic algorithm are provided on the basis of human experience and are combined with the PUN, thereby further improving the packing precision and efficiency. Also provided are a system for cooperating packing actions and unpacking actions of mechanical arm based on DRL, a computer-readable storage medium, and an electronic device.

Method and system for cooperating packing actions and unpacking actions of mechanical arm based on deep reinforcement learning

An elevator operation quality detecting system and a detecting method. The system comprises an elevator operation quality detector; the elevator operation quality detector comprises a power supply having a charging function, a central processing module, and a data transmission module, a data storage module, a data acquisition module and a touch display module which are connected to the central processing module; the data acquisition module is connected to a signal sensing module; the signal sensing module comprises a tri-axial acceleration sensor and a tri-axial angular velocity gyroscope which are both connected to the data acquisition module; the data transmission module comprises a GPRS wireless transmission module and a USB interface circuit which are both connected to the central processing module; the central processing module is a DSP main controller.

Elevator operation quality detecting system and detecting method

A heating method traction battery. The traction battery is connected to a switch circuit of a motor and configured to supply power to the motor via the switch circuit. The switch circuit includes multiple legs and the multiple legs are connected to the traction battery in parallel. The method includes: receiving a heating signal sent by a battery management system of the traction battery; and controlling, according to the heating signal, at least one of the multiple legs to form a short-circuit loop of the traction battery, the short-circuit loop being configured to discharge the traction battery and heat the traction battery during the discharging process.

Heating method and heating system of traction battery

A prestressed tensioning device and a reinforcement method that is suitable for shield tunnels, pertaining to the technical field of shield tunnel construction and reinforcement technology. The device comprises: two sets of reinforcement components, wherein the reinforcement components are arranged opposite each other; a prestressing component disposed between the two sets of reinforcement components; and a prestressing rod disposed within the prestressing component. The prestressing rod is subjected to prestress tensioning by the prestressing component, wherein both ends of the prestressing rod extend beyond the prestressing component. Both ends of the prestressing rod are connected to the two sets of reinforcement components via high-strength nuts. The present invention utilizes an articulated structure, enabling the reinforcement components to adapt to handhole angles of tunnel segments with varying diameters, and is suitable for application within confined and smooth annular structures.

Articulated prestressing tensioning device for shield tunnels and reinforcement method thereof

A method and a system for rhythmic motion control of a robot based on a neural oscillator, including: acquiring a current state of the robot, and a phase and a frequency generated by the neural oscillator; and obtaining a control instruction according to the acquired current state, phase and frequency and a preset reinforcement learning network so as to control the robot. The preset reinforcement learning network includes an action space, a pattern formation network and the neural oscillator. A control structure designed by the present disclosure, which is composed of the neural oscillator and the pattern formation network, can ensure formation of an expected rhythmic motion behavior; and meanwhile, a designed action space for joint position increment can effectively accelerate the training process of rhythmic motion reinforcement learning, and solve a problem that design of the reward function is time-consuming and difficult in learning with existing model-free reinforcement learning.

Method and system for rhythmic motion control of robot based on neural oscillator

Embodiments of the present disclosure provide a winder system that includes a battery winder and a camera apparatus. The battery winder is configured to wind a positive electrode plate and a negative electrode plate of a battery. The camera apparatus includes: a camera and a lens, where an angle between a sensor target plane of the camera and a lens plane of the lens is a predetermined angle, and the predetermined angle is greater than 0 degree and less than or equal to 20 degrees. The camera apparatus is configured to obtain images of the positive electrode plate and images of the negative electrode plate concurrently. The camera apparatus according to the present disclosure can implement focusing of images on different working planes, thereby obtaining clear images of both positive electrode features and negative electrode features concurrently with a single camera.

Camera apparatus and winder system

A winding device includes a pair of outer pins oppositely arranged in a first direction with a periphery for an electrode assembly to wind around, adjusting members configured to reciprocate in a second direction perpendicular to the first direction to drive the pair of outer pins to move away from or close to each other to increase or reduce a distance between the pair of outer pins, a pair of inner pins arranged oppositely in the first direction between the pair of outer pins and configured to move independent of the adjusting members to clamp or release the electrode assembly, and an elastic returning member configured to apply an elastic force in the first direction to at least one of the pair of inner pins such that the pair of inner pins have a tendency to be close to each other.

Winding device, winding apparatus and winding method

A method for controlling motions of a quadruped robot based on reinforcement learning and position increment, including: acquiring motion environment information, quadruped robot attitude information, and foot sole position information; based on the acquired information, generating foot sole positions of the quadruped robot during motions within all preset time steps, and calculating a change of the foot sole positions in all the time steps; taking a maximum moving distance within a single time step as a constraint, and accumulating the time steps at the same time to obtain a foot sole position trajectory; and controlling the quadruped robot to perform corresponding actions based on the foot sole position track combined with a preset reward function, so as to keep motion balance of the quadruped robot.

Method for controlling motions of quadruped robot based on reinforcement learning and position increment

The present invention discloses a method for adaptively role-selection in coordinated multi-robot search task and system thereof, comprising: defining a role action space as two discrete values: [explore, cover]; acquiring and inputting local perception information oand joint perception information jointo a role policy, and outputting a role action ρ; wherein, the local perception information comprises an obstacle map, an explored map, a covered map, and a position map; and, the joint perception information comprises a merged explored map and a merged covered map; inputting the local perception information oand the output role action ρinto a primitive policy, and outputting a primitive action aof robot to interact with the environment; then, a robot is controlled to execute corresponding output primitive action aaccording to received specific role action ρ.

Method for adaptively role-selection in coordinated multi-robot search task and system thereof

Disclosed is an automatic leveling CFRP plate pre-stressing and tensioning device for a curved surface structure, including a fixed end mechanism and a tension end mechanism, one end of the CFRP plate is connected to the fixed end mechanism and the other end is connected to the tension end mechanism, and the fixed end mechanism cooperating with the tension end mechanism to reinforce a curved surface. The fixed end mechanism includes a fixed end base plate, a fixture, a fixed end CFRP plate clamping plate, and a second high-strength bolt. The fixed end base plate is provided with a slide groove, the fixture is hinged within the slide groove by the second high-strength bolt; the fixture is provided with a fixture groove, and a size of the fixture groove decreases from one end of the fixture near the tension end mechanism to the other end of the fixture.

Automatic leveling carbon fiber reinforced polymer (CFRP) plate pre-stressing and tensioning devices for curved surface structures

An anti-loosening bolt and nut assembly includes a bolt, a nut, and a locking member. A screw rod of the bolt has an upper portion formed with an external thread and a lower portion formed with a retaining section. The nut has an upper cavity formed with an internal thread and a lower portion formed with a locking section. The locking section has elasticity. When the locking section is pressed, the locking section is in tight fit with the retaining section. The locking member is sleeved on the locking section. The locking member has an inner cavity with a tapered section. When the locking member is rotated, the nut is moved axially for the tapered section to be pressed against the locking section tightly. The bolt and nut assembly provides an anti-loosening effect, has few parts, and can be operated easily in a narrow space.

Anti-loosening bolt and nut assembly

A method and device for determining an available capacity of a battery, a battery management system, and a storage medium, relating to the field of battery technologies. The method includes: obtaining the at least one DOD interval corresponding to the SOC interval of the operation of the battery, and the number of cycles and the cycle temperature corresponding to the at least one DOD interval; obtaining a recoverable amount of capacity fade of the battery according to the at least one DOD interval, the number of cycles and the cycle temperature, and determining an actual available capacity of the battery.

Method and device for determining available capacity of battery, management system, and storage medium

Disclosed are a method and an apparatus for controlling multileaf collimator in radiotherapy. The method comprises: acquiring a preset model; outputting, regarding a radiotherapy target, a target leaf sequence of a multileaf collimator through the preset model, to obtain a planning file; and importing the planning file into a radiotherapy planning system to control a linear accelerator to operate, so as to implement a radiotherapy plan, which solves the technical problem in the related art of poor accuracy and stability in determining a leaf sequence of a multileaf collimator.

Method and apparatus for controlling multileaf collimator in radiotherapy

A cell winding calibration method includes: obtaining a first reference distance between first and second reference lines; obtaining a reference number of pixels included in the first reference distance, and determining, based on the first reference distance and the reference number of pixels included in the first reference distance, an actual distance corresponding to a single pixel; obtaining an actual number of pixels included in a distance between an edge of a winding substrate and the first or second reference line, and determining real-time position information of the edge of the winding substrate based on the actual number of pixels included in the distance between the edge of the winding substrate and the first or second reference line and the actual distance corresponding to a single pixel; and calibrating the winding substrate based on the real-time position information of the edge of the winding substrate.

Cell winding calibration method, apparatus, and device, and cell winding system

A control method for a bi-directional DC/DC converter. A source terminal transmits electric energy to a destination terminal sequentially through a first rectifier module and a second rectifier module of the converter. The method includes obtaining a first voltage value output by the first rectifier module in a current control cycle, obtaining a second voltage value output by the second rectifier module in the current control cycle, calculating a theoretical voltage control quantity of the bi-directional DC/DC converter in the current control cycle based on a preset reference voltage value and the second voltage value, and setting an actual output voltage of the bi-directional DC/DC converter in a next control cycle based on the theoretical voltage control quantity and the first voltage value.

Bi-directional DC/DC converter, control method and apparatus thereof, and storage medium

Growing community of inventors

Ningde, China

Wei Zhang