Abstract: An electro-hydraulic riveting tool has a riveting working head and a pump body. The riveting head consists of a cylinder block, a hollow piston shaft, and a rear end cover. The cylinder block and the rear end cover jointly define a hydraulic cavity. Inside the cylinder body, a first oil passage and a second oil passage are formed. On the pump body, a third oil passage and a fourth oil passage are provided. A broken-nail guide tube is coupled to the riveting working head. The rear end of the broken-nail guide tube is in communication with a nail-collecting box. An adapter plate is sleeved around the outer wall of the broken-nail guide tube. The adapter plate contains an intermediate oil passage with a first and a second intermediate oil passage. An accommodation groove is formed in the adapter plate, and a shock-absorbing joint is housed within this groove.

Abstract: A high-strength ring groove rivet includes a gun head assembly, a driving mechanism, a transmission mechanism, a power source and a control module arranged in a riveting tool shell. The transmission mechanism has a planetary roller lead screw shaft in coaxial driving connection with the clamping jaw of the gun head assembly, and is also in driving connection with the driving shaft of the driving mechanism through gears installed on the planetary roller lead screw shaft and the driving shaft of the driving mechanism respectively. The planetary roller lead screw is adopted as a component for converting rotary motion into linear motion, the output tension can reach 70 kN, and riveting installation of ring groove rivets with the diameter specification of 12 mm can be effectively completed.

Abstract: A single groove single-sided fastener comprises: a rivet consisting of a rivet head, a polish rod, a locking groove, a tail pulling groove and a tail tooth in sequence, and a lantern ring consisting of a sleeve and a dead head; a tail of the rivet is of a single groove short-tail structure, a ratio of a length of the tail pulling groove to a total length of the tail tooth is 0.1˜1.5, an included angle between a bottom generatrix of the tail pulling groove and an axis of the rivet is ?30°˜0°, two axial ends of the bottom of the tail pulling groove and the tail of the tail tooth are of a fillet transition structure, a ratio of a length of a straight part of the tail tooth to the total length of the tail tooth is 0.1˜1.

Abstract: A single groove single-sided fastener comprises: a rivet consisting of a rivet head, a polish rod, a locking groove, a tail pulling groove and a tail tooth in sequence, and a lantern ring consisting of a sleeve and a dead head; a tail of the rivet is of a single groove short-tail structure, a ratio of a length of the tail pulling groove to a total length of the tail tooth is 0.1˜1.5, an included angle between a bottom generatrix of the tail pulling groove and an axis of the rivet is ?30°˜?0°, two axial ends of the bottom of the tail pulling groove and the tail of the tail tooth are of a fillet transition structure, a ratio of a length of a straight part of the tail tooth to the total length of the tail tooth is 0.1˜1.

Abstract: An intelligent riveting system comprising a hydraulic riveting tool (1), a riveting position identification system, a riveting displacement detection system, a riveting pressure detection system and a central processing system, wherein the central processing system acquires image information and carries out position identification, encoding and storage to form riveting position data in one-to-one correspondence, acquires real-time displacement data and riveting oil pressure data of each riveting position to form real-time data corresponding to riveting displacement values and riveting pressure values, and compares same with a standard to carry out quality determination. By means of the intelligent riveting system, a riveting position and an installation parameter are automatically identified and acquired, and the riveting quality is automatically determined; and by means of storing data during riveting and installation, the traceability of rivet installation quality can be achieved.

Abstract: The present invention discloses a riveting robot, comprising: a robot part provided on a chassis, and detachably coupled with a riveting tool part through a hydraulically quick change disk; a visual position identification part provided on a side of the hydraulically quick change disk and secured on the sixth axis of the front end of the robot part; an automatic rivet feeding part provided on a mounting baseplate which is secured on a chassis through a two-stage vibration damping structure; a riveter tailing material collection part used for collecting tailing materials produced during riveting; a riveting quality judgment part used for collecting riveting data, and processing and generating a riveting curve to realize judgment of the riveting quality.

Abstract: The present invention discloses a riveting robot, comprising: a robot part provided on a chassis, and detachably coupled with a riveting tool part through a hydraulically quick change disk; a visual position identification part provided on a side of the hydraulically quick change disk and secured on the sixth axis of the front end of the robot part; an automatic rivet feeding part provided on a mounting baseplate which is secured on a chassis through a two-stage vibration damping structure; a riveter tailing material collection part used for collecting tailing materials produced during riveting; a riveting quality judgment part used for collecting riveting data, and processing and generating a riveting curve to realize judgment of the riveting quality.

Abstract: A method for obtaining road marking data and a device thereof are provided. The method includes steps of: obtaining coordinates of calibration references on a to-be-marked road; importing the coordinates of the calibration references into an electronic image of the to-be-marked road; determining, according to a difference between the coordinates of the calibration references and coordinates of to-be-calibrated points corresponding to the calibration references in a road image included in the electronic image, whether to perform a calibration on the coordinates of the to-be-calibrated points; and when the difference is greater than a threshold, performing the calibration on the coordinates of the to-be-calibrated points, and using calibrated coordinates of the to-be-calibrated points as road marking data. By applying the present disclosure, the accuracy of road marking data can be improved.

Abstract: An intelligent riveting system comprising a hydraulic riveting tool (1), a riveting position identification system, a riveting displacement detection system, a riveting pressure detection system and a central processing system, wherein the central processing system acquires image information and carries out position identification, encoding and storage to form riveting position data in one-to-one correspondence, acquires real-time displacement data and riveting oil pressure data of each riveting position to form real-time data corresponding to riveting displacement values and riveting pressure values, and compares same with a standard to carry out quality determination. By means of the intelligent riveting system, a riveting position and an installation parameter are automatically identified and acquired, and the riveting quality is automatically determined; and by means of storing data during riveting and installation, the traceability of rivet installation quality can be achieved.

Abstract: A machine learning model training method includes: classifying samples having risk labels in a training sample set as positive samples and classifying samples without risk labels in the training sample set as negative samples; training a risk model with a machine learning method based on the positive samples and the negative samples; obtaining a risk score for each of the negative samples based on the trained risk model; identifying one or more negative samples in the training sample set that have a risk score greater than a preset threshold value; re-classifying the one or more negative samples in the training sample set that have a risk score greater than the preset threshold value as re-classified positive samples to generate an updated training sample set from the training sample set; and re-training the risk model with the machine learning method based on the updated training sample set.

Abstract: A computer-implemented user classification method includes: obtaining, by a target terminal device, an initial user classification model from a server, in which the initial user classification model is provided by the server to multiple terminal devices, the multiple terminal devices including the target terminal device; obtaining first operation data of a registered user of the target terminal device; updating the initial user classification model based on the first operation data, to obtain an updated user classification model that is personalized for the registered user; and classifying, based on the updated user classification model, an identity of a current user of the target terminal device.

Abstract: A machine learning model training method includes: classifying samples having risk labels in a training sample set as positive samples and classifying samples without risk labels in the training sample set as negative samples; training a risk model with a machine learning method based on the positive samples and the negative samples; obtaining a risk score for each of the negative samples based on the trained risk model; identifying one or more negative samples in the training sample set that have a risk score greater than a preset threshold value; re-classifying the one or more negative samples in the training sample set that have a risk score greater than the preset threshold value as re-classified positive samples to generate an updated training sample set from the training sample set; and re-training the risk model with the machine learning method based on the updated training sample set.

Abstract: A method for obtaining road marking data and a device thereof are provided. The method includes steps of: obtaining coordinates of calibration references on a to-be-marked road; importing the coordinates of the calibration references into an electronic image of the to-be-marked road; determining, according to a difference between the coordinates of the calibration references and coordinates of to-be-calibrated points corresponding to the calibration references in a road image included in the electronic image, whether to perform a calibration on the coordinates of the to-be-calibrated points; and when the difference is greater than a threshold, performing the calibration on the coordinates of the to-be-calibrated points, and using calibrated coordinates of the to-be-calibrated points as road marking data. By applying the present disclosure, the accuracy of road marking data can be improved.

Abstract: The present application discloses a display panel test structure for testing whether signal lines of a display panel are defective, the signal lines at least comprising a plurality of data lines which are divided into N groups, the display panel test structure comprising N first shorting bars arranged in a test area of the display panel, each of which being configured to short-circuit a group of data lines, wherein the display panel test structure further comprises a plurality of first test pads arranged in the test area, each of which connects with one shorting bar corresponding thereto, and each of the first test pads is configured to load a signal to a group of data lines corresponding thereto during a test.

Abstract: The present application discloses a display panel test structure for testing whether signal lines of a display panel are defective, the signal lines at least comprising a plurality of data lines which are divided into N groups, the display panel test structure comprising N first shorting bars arranged in a test area of the display panel, each of which being configured to short-circuit a group of data lines, wherein the display panel test structure further comprises a plurality of first test pads arranged in the test area, each of which connects with one shorting bar corresponding thereto, and each of the first test pads is configured to load a signal to a group of data lines corresponding thereto during a test.