Hunan University

Yaonan Wang

Hui Zhang

He Xie

Jianxu Mao

Wei Sun

Li Zhou

Hongjin Wang

Qing Zhu

Yunze He

You Wu

Songyun Deng

Baoyuan Deng

Yiqin Liang

Ziming Tao

Zhenguo Zhang

Kai Zeng

Hai Qin

Caiping Liu

Junfei Yi

Zhanjin Deng

Qiaokang Liang

Xian'en Zhou

Min Liu

Haoran Tan

Xiang Li

Xueming Zhang

Chenzhuolei Chao

Provided are a method and apparatus for single-pixel thermal imaging detection of surface and internal defects of a material. The laser module is configured to generate uniform laser light. The spatial light modulation module is configured to spatially encode and modulate received uniform laser light. The projection lens module is configured to project and amplify an encoded light field, and project the encoded light field onto a surface of an object under detection. The optical convergence coupling module is configured to capture and image thermal radiation of the object under detection, and integrate and sum thermal radiation intensities of a projection heating area to obtain a thermal radiation temperature. The thermal infrared single-pixel detector is configured to measure the thermal radiation temperature. The image reconstruction module is configured to sparsely reconstruct data, and finally reconstruct a defect detection result of the projection heating area.

Method and apparatus for single-pixel thermal imaging detection of surface and internal defects of material

Disclosed in the present invention is a neural network-based defect detection method for gluing quality on aircraft skin. The method includes: data acquisition: taking photos of aircraft skin by using a camera to acquire image data; preprocessing the acquired image data; annotating the data by using annotation software to acquire a data set for network training; establishing a defect detection network model based on feature erasure and boundary refinement, where the defect detection network model includes a feature extraction network, a semantic-guided feature erasure module, a multi-scale feature fusion network, and a defect prediction network based on boundary refinement, which are sequentially connected, the data set is used for training the network model, and trained model parameters are saved; and detecting a directly collected skin gluing image by using the trained network model and outputting detection results.

Neural network-based defect detection method for gluing quality on aircraft skin

The provided is a data-driven bipartite consensus control method for multi-robot collaborative rotation of a large workpiece. The method includes: setting a multi-robot system; constructing and discretizing a dynamics model of a follower robot, and constructing a lateral error based on position information between the follower and leader robots; constructing an unknown nonlinear function with the lateral error and a control input as variables, and constructing a lateral error data model of the follower robot through a dynamic linearization technique; designing, based on a topological relationship of the multi-robot system and the lateral error, a bipartite consensus error; substituting the data model into a designed objective function to solve a data-driven bipartite consensus controller; designing a parameter estimation algorithm to estimate an unknown parameter in the controller; allowing an estimated value to participate in a controller update; and calculating a front wheel steering angle control signal.

Data-driven bipartite consensus control method for multi-robot collaborative rotation of large workpiece

A collaborative-manipulation robotic arm for kitchen waste and a working method thereof are provided. The robotic arm includes: a base, including a transverse first mounting seat and a second mounting seat connected to the first mounting seat and extending downward; a driving mechanism, disposed at an end of the first mounting seat away from the second mounting seat; a front guide claw, an upper end of the front guide claw being connected to the driving mechanism; a fixed blade, disposed on a side of the second mounting seat facing the front guide claw; and a retractable finger, disposed at a lower end on the side of the second mounting seat facing the front guide claw. The fixed blade, the retractable finger, and the second mounting seat form a rear cutting claw.

Collaborative-manipulation robotic arm for kitchen waste and working method thereof

A workpiece and cutter pose calibration method based on robotic edge milling error tracking, including: 1. generating an edge milling trajectory point cloud; 2. obtaining an actual edge milling three-dimensional point cloud; 3. generating an updated edge milling three-dimensional point cloud; 4. calculating an edge milling allowance error and a posture inclination error; 5. solving position errors of the workpiece and cutter; 6. solving posture errors of the workpiece and cutter; 7. updating pose parameters of the workpiece and cutter; 8. repeating steps 4 to 7 until pose error vectors of the workpiece and cutter are both not greater than corresponding preset thresholds. The disclosure performs error comparison, error modeling, and error tracking on the three-dimensional point cloud and edge milling trajectory point cloud, even if the cutter has system errors such as axis deviation, the disclosure can accurately identify pose errors of the workpiece and cutter during edge milling.

Workpiece and cutter pose calibration method based on robotic edge milling error tracking

A method for merging surface skin three-dimensional (3D) data includes the following steps: 1. constructing actually-measured 3D data of a workpiece and 3D data of a design model of the workpiece; 2. calculating a normal vector, a neighborhood radius, and a position of a sphere center of each point in the design model 3D data; 3. finding closest points to the design model 3D data for all points in the actually-measured 3D data; 4. calculating a static closest distance and a dynamic closest distance from each point in the actually-measured 3D data to the closest point in the design model 3D data; 5. constructing an objective function of a surface adaptive distance; 6. minimizing the objective function and calculating a differential motion screw; and 7. updating the actually-measured 3D data and achieving data merging.

Method for merging surface skin three-dimensional data

Growing community of inventors

Hunan, China

Yaonan Wang