Search

Water and fertilizer control equipment generally controls different matching ratio between water and fertilizer to achieve the integration of water and fertilizer irrigation. Most of the current machine for matching water and fertilizer cannot make fertilizer flow quickly track changes of water flow. To solve this problem, first of all, STM32F103ZET6 acts as the core of controller, the controller will output different PWM signal to change output voltage of DC motor driver, then the fertilizer flow can vary according to the water flow changes, and keep water and fertilizer holding at a set proportion; Secondly, in order to ensure the control precision, incremental PID algorithm is used to control the ratio of water and fertilizer, and RBF neural network is used to build the online parameter setting model to achieve precise and quick ratio control. Finally, using incremental PID and RBF- PID model, the simulation model is designed and different flow ratio and water flow are set up to validate the test. The result shows that the 5 kinds of different flow ratios and changes in water flow conditions, the highest average relative error of RBF-PID model is 7.55%, the highest coefficient of variation is 11.9%, the slowest flow ratio arrival time is 13s; through the test, RBF - PID model is more accurate and stable controlling than the incremental PID model.

The traditional manual counting wafers leaded to the silicon wafer cracked by operating frequently. Instead of the manual work, this paper proposed a system to counting wafers based on Machine Vision theory and Image Processing algorithm. We designed a counter system and adopted infrared led as parallel illumination source. In image pre-processing, this paper presented a series of algorithms, which contained image smoothing, uneven image correction and image morphology operation. This paper proposed a vertical projection counting based on statistics analysis substitute for the Hough straight lines detection, and the method had been achieved ideal effects by experimental results. DOI : http://dx.doi.org/10.11591/telkomnika.v12i5.5108

Solar panels laminator mainly adopt the PWM control on heating power of heat conduction oil, then the heat conduction oil will cyclic transfer heat to laminated platform, to complete the process of heating. This paper aims to study a hybrid algorithm. This algorithm combined with a fuzzy control and fuzzy self-adaptive PID control algorithm. By calculating and analysing the input variables that the temperature difference between actual temperature and set temperature on the laminated platform and the temperature difference change rate, it received output control variables to change duty cycle which control heat intensity of heat conduction oil and at last to make laminated platform temperature meetting laminated requirements.

This paper describes a kind of temperature control system which is composed of PLC. Fuzzy control algorithm was used for the system. The basic structure of fuzzy control, parameter design, and system software and hardware design was expounded. In this system, fuzzy control achieved reasonable optimization of heating time and saving electric energy of the heating element. In practical applications, the system reached practical need which embodies energy saving and, high efficient, etc.

Image segmentation is one of the key steps in image analysis, where the fuzzy theory based methods are widely used?but, none had universally property to segment all types color images. So, to improve segmentation quality and universally property of segmentation algorithm, a new fuzzy color image segmentation algorithm was brought out based on feature divergence and fuzzy dissimilarity. The algorithm measured the otherness of two stylebooks space eigenvector by feature divergence, and extracted sub-images feature eigenvector using watershed algorithm, depressed operation data number. Combination of sub-image was done by dint of fuzzy dissimilarity and morphological theory, and the isolated points were eliminated, and made color image segmentation more according with the human segmentation strategy. The method efficiency and feasibility were confirmed by experimental results.

In view of the camera calibration existent questiones, on the basis of Stereo Vision,a new method of camera calibration for binocular vision based on genetic programming is proposed. It is used to learn the relationships between the image information and the 3D information. For two-cameras system, the complicated relation between the cameras is established by training the genetic programming without the parameters of the cameras calibrated. It neither requires an accurate mathematical model nor needs any prior knowledge about the parameters. The 3D information of target is achieved from genetic programming output.The results of the experiment showed that this method was more accurate with traditional visual calibration methods.