×

You are using an outdated browser Internet Explorer. It does not support some functions of the site.

Recommend that you install one of the following browsers: Firefox, Opera or Chrome.

Contacts:

+7 961 270-60-01
ivdon3@bk.ru

  • Design of the SPI slave based on gate arrays

    Results of the Serial Peripheral Interface (SPI) Slave node design based on gate arrays 5503 series are presented in this paper. SPI is used for high-speed synchronous data transmission between control and peripheral devices. Developed chip could be applied in connection with SPI Master node for matching microcontrollers and microprocessors with different sensors, analog-to-digital and digital-to-analog converters, memory and communication units. Upon the results of the development, design approach of digital integrated circuits is proposed. The approach supposes using Russian freeware CAD "Kovcheg" ("Ark") designated for gate arrays design (IC based on prefabricated crystals, components on which are supposed to be interconnected during design to form logic devices). According to the proposed approach, behavioural descriptions of the devices, written on hardware description languages (e.g. Verilog), are used, since it is often easier to describe circuit operational principal algorithmically than construct structure from components library. The problem is that "Kovcheg" can't execute structural synthesis of the circuit from behavioural description. So it is proposed in the approach to use outside CAD environments, intended even for design of custom full-integrated circuits (like Cadence) or FPGA (like Vivado), to synthesize structural description of desired device from known behavioural ones and available process design kits (PDK) or library, appropriate for the chosen CAD. The entire design cycle using "Kovcheg" is outlined in the paper.

    Keywords: gate arrays, serial peripheral interface, hardware description language, computer-aided design

  • Volumetric modeling of a microwave liquid heater

    This work is devoted to modeling the absorption of microwave electromagnetic field energy in a device for milk pasteurization. Using CAD FEKO, a 3D model of the device was built and its operation was simulated. A study was made of the influence of the tilt angle of quartz tubes on the distribution of the electromagnetic field in the waveguide. The influence of the diameter and material of the tubes is also considered. The distributions of the electric field and the specific power absorbed per kg of dielectric in the waveguide are obtained. The accuracy of the results was assessed.

    Keywords: pasteurization, microwave, heat treatment of dielectrics

  • Algorithm for marking related areas in streaming image processing

    The problem of choosing the desired image segmentation algorithm and its real-time implementation arises in systems that work with a high-speed video data stream. Labeling related areas is an important step in preparing images for neural network training set. In this paper a modified one-pass image labeling algorithm for use in field-programmable gate arrays (FPGAs), as well as its implementation using the Xilinx System Generator for DSP and the Matlab/Simulink package was proposed. The results of the algorithm operation on test images, as well as images obtained experimentally, are presented. This algorithm was developed to analyze and evaluate the quality of wheat seeds by classifying their images using artificial intelligence.

    Keywords: labeling of related areas, artificial intelligence, segmentation, stream processing

  • Wheat seed quality assessment based on convolutional neural network algorithm

    The article proposes a method for analyzing and assessing the quality of wheat seeds by classifying their images using artificial intelligence, namely a convolutional neural network. The architecture of a deep convolutional neural network was proposed, an image base was created for training and testing the proposed neural network, training and testing of the neural network was carried out in Tensorflow. Conclusions about the efficiency of image classification are made and areas of use of the proposed method for analyzing and assessing the quality of wheat seeds are proposed.

    Keywords: convolutional neural networks, artificial intelligence, image classification

  • Preparing a dataset for training and testing neural networks in MATLAB

    The paper proposes a method for preparing a dataset for training and testing neural networks in the MATLAB environment using the Image Processing Toolbox package of functions. An example of the implementation of this technique for preparing a dataset for training convolutional neural networks to classify wheat seeds into high-quality and low-quality classes according to its images is given. This technique was used to obtain a dataset of 900 images, which were successfully used to train and test the convolutional neural network.

    Keywords: dataset, convolutional neural networks, artificial intelligence, image classification

  • Research of the spatial distribution of microstructural and electrical parameters in a powerful convective cloud based on a three-dimensional numerical model

    The paper considers the characteristics of cloud convection obtained in the course of computational experiments on the basis of a three-dimensional physical and mathematical model of convective clouds, which takes into account in detail the microphysical processes of nucleation, condensation or sublimation of water vapor, coagulation and accretion of precipitation particles, accumulation of volume electric charges, and an increase in the electric field strength. clouds due to charge separation processes occurring during the rapid freezing of large supercooled drops, accretionary growth of cereals and hailstones. Based on the data of numerical modeling using the noted model, the location in the volume of the microstructural parameters of thunderstorm clouds (water content and ice content), space charges, electric field strength, radar reflectivity in the centimeter range, and other parameters at fixed times of cloud evolution was investigated.

    Keywords: convective cloud, cloud microstructure, cloud electricity, numerical three-dimensional model, radar reflectance, electrical coagulation

  • Methods for diagnosing engineering objects based on neural networks

    Rail transport plays a key role in the transport of passengers and goods. The high demand for effective means of flaw detection of high-speed rails, which is an important component of railway safety, is justified by the constantly growing number of vehicles and their speed [2]. Failure of elements of the railway infrastructure entails huge losses. In this regard, the analysis and forecasting of the state of elements of the railway infrastructure is an urgent task. This article analyzes modern methods for diagnosing the state of a rail track from a mobile bogie or a conventional locomotive. A method for diagnostics of a rail track is proposed, based on registration of vibrations near the rolling surface of rails and processing these signals using neural networks.

    Keywords: rail flaw detection, wheel surface, algorithm, IMM, MEMS, control system, inertial sensor, rail defect, contactless measurement

  • Investigation of surface morphology and electrical silicon film after laser annealing

    Currently, laser annealing are widely used to create a polycrystalline silicon film, which is promising for use in thin film solar cell, and transistors, liquid crystal displays and sensors due to recrystallization of amorphous and nanocrystalline silicon films. The study of morphology and surface conductivity of single-crystal silicon film on a glass substrate by laser annealing power. Laser annealing is carried Nd: YAG laser with a wavelength of 532 nm, speed of movement of the stage with a specimen of 5 mm/s and a laser power ranging from 34 to 86 watts. The laser beam was focused on the sample in the form of a narrow line width of 10 microns and 60 mm in length. The dependence of the size of the nanocrystals and the conductivity of silicon films on the power of the laser annealing radiation. It is shown that the power of the laser radiation in the range of 60 to 70 W is optimal for the best electrical parameters silicon film for the purpose of its use in high-performance thin-film solar cells.

    Keywords: silicon film, laser annealing, surface morphology, electrical conductivity, thin film solar cell

  • Intelligent technique for faults prediction on hump yards

    Nowadays the wide integration of automation resources is occurred in many domains of industry. One of the key aspects of this process is control automation for breaking up process on railways. Due to the fact that main element of railway yard is hump the Intellectualization of decision making processes becomes the key task in area of fault prediction during breaking up. The experience of fault effects elimination shows this task decision allows to reduce the financial and time costs for breaking up process. This paper proposes new algorithm for creation of theoretical base of the system for fault prediction. This algorithm is realized by hybrid methods, which combine different temporal models characterizing technological process of sorting of following cuts. Presented experimental arguments show integration of proposed methods is efficient in domain of railway nreaking up process

    Keywords: breaking up process, hump yards automation, intellectualization of technological processes, fault detection, hybrid techniques, fuzzy temporal relations, reconstructed phase space