No abstract

No abstract

Vision based robot applications have taken a great deal of attention, with the development of electronic and computer technology. The visual feedback loop is very effective for improving the dexterity and flexibility. In this study, application of real time visual servoing approach is presented that enables a robot to robustly execute arm grasping and manipulation tasks. This task is decomposed on four stages a) finding object b) determining object's pose c) moving the robotic arm from an initial position towards the object d) grasping the object. The robot used in this work consists of an arm and head parts. The robotic arm has six degree of freedom, five degree of freedom are located at the arm while one degree of freedom is assigned to the gripper. Head has two degree of fredom which is pan-tilt platform. The image-based control strategy is designed using Fuzzy-PID controller. In this way, position error between target object and griper is minimized and the gripper can grasp the target object precisely. Real-time implementation of the proposed method is carried out using Matlab-Simulink. Experimental results show that, the developed design is valid to detect and grasp objects in real time.

Drawbeads are often used in the sheet metal forming processes to provide a better control of the material flow into the die cavity. The drawbead restraint force (DBRF) and the exit thickness are two important sheet drawing characteristics to be determined for the selection and installation of the drawbead elements. This study presents the effects of drawbead geometry and sheet material on drawbead restraining force and thinning. Mathematical correlation between the drawbead geometry, sheet material and drawing characteristics was investigated by using Response Surface Methodology (RSM), which is a global approximation method ideally suited for solving highly nonlinear optimization problems. The proposed response surface model for DBRF and thinning showed a good correlation with the experimental data available in the literature. RSM could be considered as an alternative and practical technique to evaluate the sheet drawing characteristics. The method can also be applied to other sheet metal forming issue.

Raw-material blending is an important process affecting cement quality. The aim of this process is to mix a variety of materials such as limestone, shale, sandstone and iron to produce cement raw meal for the kiln. One of the fundamental problems in cement manufacture is ensuring the appropriate chemical composition of the cement raw meal. A raw meal with a good fineness and well-controlled chemical composition by a control system can improve the cement quality. The first step in designing a control system for the process is obtaining an appropriate mathematical model. In this study, Linear and Nonlinear Neural Network models were investigated for the raw-material blending process in the cement industry and their results were compared with the experimental data. The results showed that the nonlinear model has a higher predictive accuracy. Keywords: mathematical modeling, cement, raw material blending, neural network Me{anje sestavin je pomemben postopek, ki vpliva na kvaliteto cementa. Naloga tega postopka je zme{ati razli~ne materiale, kot so: apnenec, {krilavec, pe{~enjak,`elezo in drugi; da se dobi surovino za cement za rotacijsko pe~. Ena od osnovnih te`av pri izdelavi cementa je zagotoviti primerno kemijsko sestavo surovine za cement. Kontrolni sistem za surovino z dobro zrnatostjo in dobro kontrolirano kemijsko sestavo, lahko izbolj{a kvaliteto cementa. Prvi korak pri postavitvi kontrole procesa je postavitev primernega matemati~nega modela procesa. V {tudiji sta bila preiskovana linearni in nelinearni model nevronske mre`e za postopek me{anja v cementni industriji in rezultati so bili primerjani z eksperimentalnimi podatki. Rezultati so pokazali, da ima nelinearni model ve~jo to~nost napovedovanja.