Cao Qixin

Study on color image processing based intelligent fruit sorting system

A machine vision system that can be used for automatic high-speed fruit sorting is proposed. Fruit area was first segmented out from image with an Ohta-color-space based thresholding algorithm; blob algorithm was utilized to remove noises in image; spline-interpolation based algorithm was adopted to detect fruit contour. In fruit sorting process, fruits color ratio, which was calculated with HSI color space, was selected as classification feature. Fruit sorting was realized by classic Bayes classifier, whose parameters were obtained by a study module. This system was tested with Crystal Fuji apples, and an average sorting accuracy of 90% was achieved.

Solar cell crack inspection by image processing

Spacecraft operate in a hostile environment, far from the Earth, so it is necessary for solar cells with anti-radiation properties to have a bonding process carried out on them. After bonding, an essential process for the solar cell assembly is to inspect for cracks on the edges or inside the solar cell. To avoid utilizing unqualified products and to improve the reliability of products, this paper presents a method to detect the cracks of solar cell by image processing. This method utilizes the gray transform, image adjustment, Gauss-Laplacian transform, contour detection, crack recognition, and so on. The validity of this method has been verified by experiment.

Operation Principle of a Bend Enhanced Curvature Optical Fiber Sensor

A curvature optical fiber sensor is reported in this paper. The curvature measurement sensitivity is improved using bend enhanced method. The operation principle of this intensity modulate macro-bend curvature optical fiber sensor is proposed based on light scattering theory: the bend of sensitive zone brings about mode coupling and leads to the variation of surface scattering loss. The mathematic model of relationship among light loss, bending curvature, surface roughness and parameters of the fibers configuration is also presented

A binocular machine vision system for ball grid array package inspection

Purpose – In this paper, an optical inspection method of the ball grid array package(BGA) is proposed using a binocular machine vision system.Design/methodology/approach – The height of each solder ball is calculated based on spatial geometrical size and location obtained from the two CCD cameras capturing range images of a LED illuminated BGA chip at certain orientation.Findings – The structure of this system is simple and the accuracy is 0.02 mm, The experimental results have proved the validity of this system for BGA failure detection.Practical implications – The developed machine vision system can provide some of the critical factors for BGA quality evaluation, such as the height of solder ball, diameter, pitch and coplanarity.Originality/value – Compared with other systems, the structure of this system is simple and accurate, which meets the demand of off‐line and on‐line inspection. The limitation of this system is that the margin of field of view (FOV) is fuzzy. Further study could be focused on th...

A corba-based simulation and control framework for mobile robots

This paper presents a distributed multiple mobile robots framework which allows programming and control of virtual and real mobile robots. The system provides the map building, path planning, robot task planning, simulation, and actual robot control functions in an indoor environment. Users can program the virtual robots in a customized simulation environment and check the performance of execution, i.e., if the simulation result is satisfying, users can download the code to a real robot. The paper focuses on the distributed architecture and key technologies of virtual robots simulation and control of real robots. A method for construction and transfer of a key index value (which stores the robot configuration) is proposed. Using this method, only the robot key configuration index is needed to build the robot in the virtual environment. This results in reduced network load and improved real time performance of the distributed system. Experiments were conducted to compare the performance of the proposed system with the performance of a centralized system. The results show that the distributed system uses less system resources and has better real time performance. What is more, this framework has been applied to Yaskawas robot “SmartPal.” The simulation and experiment results show that our robotic framework can simulate and control the robot to perform complex tasks.

Machine Performance Degradation Assessment Based on PCA-FCMAC

A PCA-FCMAC (Principal Component Analysis-Fuzzy Cerebellar Model Articulation Controller) model is proposed for machine performance degradation assessment. In the model, the selected features from the sensor signals are first processed by PCA to eliminate the redundant information and then inputted into FCMAC. FCMAC is used to assess degradation states quantitatively based on its local generalization ability. The implementation of the model is presented. Then the application in a drilling machine to assess the states of the cutting tool shows the effectiveness of the model. The comparative analyses of the assessing results prove FCMAC work better than CMAC.

A Distributed Control and Simulation System for Dual Arm Mobile Robot

In order to realize the dual arm mobile robot control and simulation, a distributed robotic system is presented. The system provides the robots model building, path planning, robot task planning, simulation and actual robot control functions in an indoor environment. This paper is focused on two major issues: the distributed systems modularity and the key technologies based on the robots key-values in robot construction and multi-robot simulation. Experiments were conducted in order to compare the performances of the proposed system with the performances of a former centralized system. The results show that the distributed system uses less system resources, has better real time performances and satisfies the requests of dual arm mobile robot.

Study on quality control in the bonding processing of space solar cell

The solar cell is widely used for space power. The characteristic of anti-irradiation is one of the important differences between ordinary solar cells and space solar cells. In order to ensure a space solar cell works reliably in the space environment, it is necessary to bond the anti-irradiation cover-glass to the space solar cell active surface using a kind of adhesive, and it is vital to have a reasonable coating thickness. Combining robotics and adhesive-coating technology, this paper gives an automatic bonding system for space solar cells, which can precisely control the coating thickness and realize bonding automation in non-vacuum conditions. Moreover, on the basis of the theory of non-Newtonian fluids, the paper presents a model for this system and deduces the formula for the coating thickness of space solar cells. Experiments have been performed to validate this model.

An RTM Based Distributed Simulation System for Guide Robot

A distributed simulation system was developed in this paper to enhance the robot system integration and development for guide robot via using RTM (Robot Technology Middleware) technology, which is an open software platform for robot systems. The RT (robot technology) system of an adapter, a controller and the robot, together with other CORBA objects was developed to connect the graphical programming interface with the 3D simulator to set up a network based simulation system. Simultaneously, the application of the distributed simulation system also confirms the controlling of the real robot utilizing the RT system. RT-Middleware can obviously accelerate the software component development and the system integration, which of course will lower the cost of the development of new robot application systems.

An image processing approach for jigsaw puzzle assembly

Purpose – To develop an image processing approach for jigsaw puzzle assembly.Design/methodology/approach – First, pixels are extracted from the jigsaw puzzle blocks to calculate their rotation angles and centre coordinates. Second, a template matching method is employed to recognise each block and its orientation.Findings – A robot‐based jigsaw puzzle system is established; and an effective image processing approach for assembly is developed.Practical implications – Automatic assembly lines that assemble parts with the same shape, but random position and angle, can employ the jigsaw puzzle assembly method.Originality/value – An effective image processing method for jigsaw puzzle assembly is presented in this paper. The validity of the method is proved by analysis and experiment.