Abstract: A method for optimizing the placement process of a surface mounter using a heuristic adaptive tabu search is presented, relevant to surface-mount technology. The method includes encoding and decoding heuristic adaptive information link, where encoded information cover component allocation sequence, head sequence, heuristic algorithm selection, and pick-and-place path optimization sequence. The decoded results configure the component allocation algorithm and pick-and-place path optimization algorithm, and the optimized placement process is derived using these configured algorithms. The component allocation algorithm includes both the available feeder-oriented heuristic algorithm and the assigned feeder group-oriented heuristic algorithm, suitable for different feeder scenarios. Optimizing the selection of these algorithms achieves adaptive optimization for various production scenarios.

Abstract: There is provided a method of performing online optimization on a pick-mount path during production of a surface mount machine and a pick-mount path optimization method of a surface mount machine is provided. In order to address the problem of too long pick-mount path resulting from poor optimal solution search capability when the existing surface mount machine performs optimization based on heuristic algorithm by calling software, the method includes: based on a mount optimization solver of the surface mount machine, obtaining an initial mount process optimization result, and transmitting the result into an industrial control computer of the surface mount machine to start surface mount production; based on the tabu search, performing comparison on the pick-mount path optimization results to select an optimal one and transmitting the newly-obtained optimal result into the industrial control computer of the surface mount machine, and then by starting from a next circuit board.

Abstract: The present disclosure relates to placement path optimization methods of a surface mount machine and in particular to a placement path optimization method of a surface mount machine based on row-column grouping genetic algorithm. The method includes the following steps: 1. obtaining production parameters and data; 2. grouping placement points into matrix rows based on rows; 3. encoding chromosomes to generate a chromosome population; 4. decoding chromosomes to obtain column grouping results for placement points and calculating placement path lengths; 5. setting parameters and loop conditions for the genetic algorithm; 6. updating optimization results based on crossover operators; 7. updating optimization results based on mutation operators; outputting the optimal placement path. This invention falls within the realm of electrical technology and electrical engineering.

Abstract: Disclosed is an intelligent micromanipulation system based on machine vision, including a base, wherein a microscope, a rotating table and two lifting tables are arranged on the base, the microscope is located right above the rotating table, the two lifting tables are arranged at two sides of the rotating table, respectively, and each is provided with a mechanical arm, each of the two manipulators is provided with an end effector, the mechanical arm is capable of driving the corresponding end effector to perform fine adjustment in x, y and z directions, one of the end effectors clamps a suction holding needle in communication with a suction pump, while the other end effector clamps an injection needle in communication with an injection pump; and the rotating table includes a tray, a rotating mechanism and a driving device, and the driving device drives the tray to rotate via the rotating mechanism.

Abstract: The present invention provides an ultra-microinjection detection and control device based on lensless imaging and a method thereof. A lensless optical liquid level sensor is used to measure a change of a liquid level in an injection needle. A microinjection control unit is used to track the change of the liquid level and correct an injection pressure of the injection pump. Transmitted light generated by a parallel light source passes through a transparent glass tube of the injection needle. Then the transmitted light passes through a light filtering film to reduce the intensity of the parallel light source to a photosensitivity range of a micro linear array image sensor chip. Finally, the transmitted light enters the micro linear array image sensor chip, so that the micro linear array image sensor chip measures the change of the liquid level in the injection needle.

Abstract: The present disclosure relates to a visual servoing method based on fusion of distance space and image feature space. The method includes: constructing an image Jacobian matrix; constructing a depth Jacobian matrix; fusing the image Jacobian matrix and the depth Jacobian matrix, to obtain a hybrid visual servoing Jacobian matrix; and obtaining a robot motion control amount according to the hybrid visual servoing Jacobian matrix by using a control algorithm, to enable a robot to move to a target position, to complete precise positioning.

Abstract: The present disclosure relates to an indoor monocular navigation method based on cross-sensor transfer learning and a system thereof. Determining an preliminary autonomous navigation model according to simulated laser radar data; acquiring actual single-line laser radar data and monocular camera data of the mobile robot simultaneously in an actual environment; determining the heading angle of the mobile robot according to the actual laser radar data; determining a laser radar monocular vision navigation model, according to the generated heading angle of the mobile robot and the monocular camera data at a the same moment and by using a Resnet18 network and a pre-trained YOLO v3 network; determining a heading angle of the mobile robot at the current moment, according to the acquired monocular camera data and by using the laser radar monocular vision navigation model; performing navigation of the mobile robot.

Abstract: The present invention relates to an indoor monocular navigation method based on cross-sensor transfer learning and a system thereof. Determining an preliminary autonomous navigation model according to simulated laser radar data; acquiring actual single-line laser radar data and monocular camera data of the mobile robot simultaneously in an actual environment; determining the heading angle of the mobile robot according to the actual laser radar data; determining a laser radar monocular vision navigation model, according to the generated heading angle of the mobile robot and the monocular camera data at a the same moment and by using a Resnet18 network and a pre-trained YOLO v3 network; determining a heading angle of the mobile robot at the current moment, according to the acquired monocular camera data and by using the laser radar monocular vision navigation model; performing navigation of the mobile robot.

Abstract: Disclosed is an intelligent micromanipulation system based on machine vision, including a base, wherein a microscope, a rotating table and two lifting tables are arranged on the base, the microscope is located right above the rotating table, the two lifting tables are arranged at two sides of the rotating table, respectively, and each is provided with a mechanical arm, each of the two manipulators is provided with an end effector, the mechanical arm is capable of driving the corresponding end effector to perform fine adjustment in x, y and z directions, one of the end effectors clamps a suction holding needle in communication with a suction pump, while the other end effector clamps an injection needle in communication with an injection pump; and the rotating table includes a tray, a rotating mechanism and a driving device, and the driving device drives the tray to rotate via the rotating mechanism.

Abstract: The present disclosure relates to a visual servoing method based on fusion of distance space and image feature space. The method includes: constructing an image Jacobian matrix; constructing a depth Jacobian matrix; fusing the image Jacobian matrix and the depth Jacobian matrix, to obtain a hybrid visual servoing Jacobian matrix; and obtaining a robot motion control amount according to the hybrid visual servoing Jacobian matrix by using a control algorithm, to enable a robot to move to a target position, to complete precise positioning.

Abstract: The present invention provides an ultra-microinjection detection and control device based on lensless imaging and a method thereof. A lensless optical liquid level sensor is used to measure a change of a liquid level in an injection needle. A microinjection control unit is used to track the change of the liquid level and correct an injection pressure of the injection pump. Transmitted light generated by a parallel light source passes through a transparent glass tube of the injection needle. Then the transmitted light passes through a light filtering film to reduce the intensity of the parallel light source to a photosensitivity range of a micro linear array image sensor chip. Finally, the transmitted light enters the micro linear array image sensor chip, so that the micro linear array image sensor chip measures the change of the liquid level in the injection needle.