Applied Mechanics and Materials Vol. 756

Abstract: This paper considers the problem of request distribution in a taxi company for workload optimization. A combined algorithm for request distribution using multi-objective optimization methods is offered.

Abstract: The article discusses the models of repair process of a turbine compressor package blades. The author determines the boundaries of the assured quality area considering mathematical model analysis and defect detection of rotor blades based on the results of natural vibration frequency measurements.

Abstract: This study describes the method of determining cutting force components in oblique turning. The scheme of how the investigations were performed is presented. The characteristic curves of cutting force components vs. thickness of the material removed, tool clearance and tool rake angles are shown. The study presents the data, which have been obtained during the experimental investigations and analytically calculated, on how the cutting forces are subject to changes depending on a cutter angle, cutting depth and feed in oblique turning operations. The analysis of approximation of the experimental results and error check of the theoretical calculations relative to the experimental data are given.

Abstract: This paper is concerned with an algorithm of determining a position of an object and its borders in an X-Ray image. The algorithm is based on a preliminary estimation of a histogram of given image. The information retrieved from estimation provides complementary parameters for further edge detection. As a result, this approach allows reducing the processing time. The future research and development of the algorithm will be aimed at object tracking in real-time systems.

Abstract: There are various vendors of FFT libraries, but there is no software available for it automatic benchmarking on all available devices. In this article an application that allows easy measure the performance and precision of various FFT libraries on the available GPUs and CPUs is presented. This application has been used to find out the fastest FFT library for NVIDIA GTX TESLA and NVIDIA GTX TITAN. The obtained results shown that the best implementation is provided by cuFFT library developed by NVIDIA.

Abstract: In this paper authors researched problems about construction of sonar images which based on signal from side-scan sonar. Authors use explicit formula for signal processing. It includes influence of volume scattering in the medium. Moreover, authors use an additional filter for signal. It is logarithm-filtration.

Abstract: The study discusses adaptive neuro-fuzzy methods of recognition of the multidimensional overlapping objects on the basis of the introduced concepts, generalized and modified operations of fuzzy set theory and neural networks. To improve recognition accuracy, proposed a combined approach including neural network analysis of generalized images based on Kohonen maps, and building systems fuzzy inference based on the identification of allocated clusters integral characteristics of the images. Using the derived system of diagnostic decision rules "If ... then" the comprehensive forecast map of oil South of Cheremshan field was built.

Abstract: This article shows the solution to the problem of designing а neuronetwork component of industrial technical system. This solution lets to provide nominal accuracy of information processing, when technical system is working under conditions of destabilizing factors.Base of designing а neuronetwork component is algorithms of elimination of influence of external and internal noise of artificial neural network developed by authors.

Abstract: The relevance of this study is stipulated by the necessity of designing techniques, algorithms, and programs improving the efficiency of automatic number plate recognition (ANPR) on images with complex backgrounds.Purpose: The aim of this work is to improve the efficiency of automatic number plate recognition on images with complex backgrounds using methods, algorithms, and programs invariant to affine and projective transformations.Design/methodology: Such techniques as artificial intelligence, pattern identification and recognition, the theory of artificial neural networks (ANN), convolutional neural networks (CNN), evolutionary algorithms, mathematical modeling, the probability theory and mathematical statistics were applied via Visual Studio and MatLab software.Findings: The software is developed allowing the automatic number plate recognition on complex background images. The convolutional neural network comprising seven layers is suggested to identify the plate localization, i.e. finding and isolating the plate on the picture. The pixel intensity histogram-based algorithm was used for character segmentation or finding individual characters on the plates. The convolutional neural network comprising six layers is designed to recognize characters. The suggested software system allows automatic number plate recognition at large angles of inclinations and rather a high speed.

Abstract: The task of analyzing digital images on the basis of local characteristics of self-similarity is considered in this article. The algorithm of forming fractal characteristics of images and the detection algorithm, which can be used to solve the problems of task detection, are described. The results of studying the possibility of distributing the self-similarity in the problems of crack-detection are given