Electronics and Control Systems
ISSN : 1990-5548
Published by: National Aviation University (10.18372)
Total articles ≅ 1,027
Latest articles in this journal
Electronics and Control Systems, Volume 4; https://doi.org/10.18372/1990-5548.66.15222
The problem of construction of deep neural networks with the use of genetic algorithms is considered. The problem of structural-parametric synthesis with creation of neural networks is defined. The main purpose of the study is to find a deep neural network that is optimal for solving urgent problems. The classification problem is chosen as the urgent problem to solve. Also the classification of genetic algorithms is given, which are used as a basis for establishing the parameters of deep neural networks A system for the optimal tuning of the parameters of deep neural networks is proposed, which includes a two-stage algorithm. At the first stage of the algorithm, a multicriteria genetic algorithm is selected from a set of possible ones (genetic algorithm of vector estimation, genetic algorithm of Fonseca and Fleming, genetic algorithm of Pareto approximation with niche, genetic algorithm of sorting without dominance, genetic algorithm of Pareto force, genetic algorithm of Pareto-2 force ) that best fits the given training sample. At the second step, the problem of structural-parametric synthesis of a neural network is solved according to the criteria of accuracy and complexity. As a result of training, the values of the neural network parameters are found, such as: the number of layers, the number of neurons in each layer, the values of the weight coefficients.The modeling of the proposed system is carried out. The results of modeling, comparison of results with similar software packages are presented. The obtained results show the possibilities of wide use.
Electronics and Control Systems, Volume 4; https://doi.org/10.18372/1990-5548.66.15232
The developed automated system of discharge of fire-extinguishing liquid from the firefighter's plane has a number of advantages, namely due to automation and more exact hit of fire-extinguishing liquid in a fire zone at zero visibility. It includes a sighting and navigation complex, which provides automatic determination of the fire zone, accurate sighting of liquid and a control system for opening tanks. The liquid discharge process is fully automated due to the implementation of the control algorithm for calculating the delay time, the discharge command taking into account the height, wind and ballistics of the discharged fluid, automating the decision on the number of open tanks. An algorithm for the process of discharging fire-extinguishing liquid for the rational use of aircraft in firefighting has been developed.
Electronics and Control Systems, Volume 4; https://doi.org/10.18372/1990-5548.66.15227
The paper deals with methods and algorithms for increasing the accuracy of unmanned aerial vehicle identification. Accumulation of data on radiation parameters during the session of observation of an object allows to make continuous specification of the made decisions by the set moment of the end of a session of observation the reliability of its identification would be sufficient for acceptance of necessary prompt actions. If to consider a problem of identification taking into account the specified specifics, then in its structure it is necessary to allocate several stages of decision-making depending on volume available for the considered moment of observation of data, conditions of their receiving and processing by the technical means of the information-measuring system. Observation system and control of objects of a sound emission represent difficult sound engineering complexes in which work not only equipment rooms and software, the knowledge base and data, but also intellectual resources of experts are involved. Decisions of different levels in such systems are made not only automatically technical means on the basis of formal algorithms, but also operators, on the basis of the and borrowed experience. Taking into account it is necessary to consider, both bases of creation of formal algorithms of decision-making, and feature of decision-making by the expert for the purpose of clarification of conditions of ensuring the maximum reliability of identification.
Electronics and Control Systems, Volume 4; https://doi.org/10.18372/1990-5548.66.15230
Тhe article deals with the problem of determining the coordinates of the location of the target based on using some lines-of-sight by means of antennas mounted on unmanned aerial vehicles. Algorithms for target positioning using an unmanned aerial vehicle are proposed. The proposed algorithms require knowledge of the coordinates of several positions of the unmanned aerial vehicle. For solving the problem, the least-squares technique is used. Some ways of solving the problem are considered. In the first case, the algorithms assume finding several lines of sight of the target. Further, either a geometric or an analytical method for solving the problem is used. In the second case, the algorithm assumes measuring the distances from the vehicle to the target. The tasks are solved in vector and vector-matrix form. The results of simulation are presented, confirming the effectiveness of the proposed algorithms. The obtained results can be useful for both civilian and special areas of application.
Electronics and Control Systems, Volume 4; https://doi.org/10.18372/1990-5548.66.15254
This paper considers a fundamentally new model of data network construction for servicing the flows given by the gravitational matrix with restrictions on the time of information transmission. The proposed network model differs from the known ones because it has an expanded capacity of node and channel resources, combining the lowest possible cost of channels and switching nodes. As part of the development of the proposed model and algorithm for allocation of flows in a full mesh network, the developed mathematical apparatus provides a high degree of reliability and survivability of the synthesized network as a whole. One of the used approaches to the solution of the linear programming problem is based on the choice of the target function, the type of which is determined by the consumer conditions of the synthesis of a particular data network. Within the framework of the article, it is established that the linear programming problem, for each specific case, has an admissible, practically realizable solution with the optimal choice of the target function without additional simplex transformations. An important obtained result of the research is the simplicity of flow control, which is in direct dependence on the strict ordering of the proposed structure, because it was possible to connect by analytical dependences the flows in the branches and the path data transfer flows. The obtained analytical results can be used as a basis for statistical algorithms of information flow control.
Electronics and Control Systems, Volume 4; https://doi.org/10.18372/1990-5548.66.15231
The issues of automation of aircraft landing control on a short runway are considered. A scheme for constructing an approach tract along a steeper glide path and with a touchdown point located at the very beginning of the runway is proposed, which makes it possible to reduce the length of the air section and the required length of the runway. Formulas are proposed for recalculating the glide path holding parameters for the implementation of automatic control of the descent and landing of the aircraft. To reduce the size of the landing zone, it is proposed to construct a landing trajectory according to the method of controlling the final state during landing along a flexible trajectory. The principles of constructing systems for automatic control of aircraft landing based on algorithms with a predictive model with a gradual approach to the forecast horizon are considered.
Electronics and Control Systems, Volume 4; https://doi.org/10.18372/1990-5548.66.15229
This article discusses the optimization problems of energy associated with the optimal management of a complex ergatic electric power system. The search for solutions to these problems is proposed to be carried out on the basis of extremization of the target functional specified using the statistical model. In order to analyze the control process of a complex ergatic electric power system, it is proposed to apply the aggregative - decomposition approach, according to which models of complex power supply systems are described by compositions of interconnected units. When searching for a solution to the optimization problem of controlling a complex electric power system, it is proposed to apply the method of stochastic programming, as well as the method of stochastic quasigradients. From the point of view of the object-oriented approach, it is proposed to consider complex ergatic electric power systems as a class of multi-level multi-purpose systems, which are the subject of cybernetics research. Moreover, the adequacy of algorithmic models for managing these systems is ensured by the implementation of compromise methods. To implement control functions at the highest hierarchical levels of complex electric power systems, it is proposed to create aggregated models of these systems using the descriptive aggregation procedure. The principles of coordination of mathematical programming problems of electric power systems are also considered, according to which local admissibility and consistency predetermines global admissibility.
Electronics and Control Systems, Volume 4; https://doi.org/10.18372/1990-5548.66.15225
The problem of generating training data for setting up the convolutional neural networks is considered, which is of great importance in the construction of intelligent medical diagnostic systems, where due to the lack of elements of the training sample, it is proposed to use the approaches of artificial data multiplication based on the initial training sample of a fixed size for the image processing (the results of the ultrasound, CT and MRI). It shows that the increase of the training sample resulted in less informative and poor quality elements, which can introduce extra errors in the goal achievement. To eliminate this situation the algorithm for assessing the quality of a sample element with the subsequent removal of uninformative elements is proposed.
Electronics and Control Systems, Volume 3; https://doi.org/10.18372/1990-5548.65.14987
The paper takes into consideration risk systems that can use not only in nuclear reactions but other plants with frequent risks for people's life, such as mining, and other. Such facilities apply information systems in which take place exchange text messages through free space. The main problem of information radio reception is an increasing number of emitting means that equal the increase of noise level receiving set. As an additional means of processing distorted textual information, it is proposed to use a neural network, which must be pre-configured. For analysis, the back propagation neural network was selected. The adjustment is carried out by an algorithm assuming a double differentiation of the error function, which ensures a high network convergence rate. Learning is stopped according to the total criterion for the deviation of the output signal from the reference. The paper formulates the conditions of quadratic convergence of the back propagation network with one new tuning procedure, and also offers examples of the construction of a neural network for recognizing a text message in various reception conditions. The fed to the neural network is sequence of the letters of English alphabet. A feature of the structure of the neural network that provides correct recognition is the use of completely nonlinear neurons. Comparison of options for the structure of the neural network when recognizing text phrases is carried out according to indicators of the probability of recognition, error, and training time. The established properties of the neural network are useful in the design of efficient information system.
Electronics and Control Systems, Volume 3; https://doi.org/10.18372/1990-5548.65.14983
The problem of acceptance control of a fifth-level automatic driving system is investigated when using nonhomogeneous samples and allowing one failure in the total sample. It is shown that by using different operating and test conditions, subdivided into normal and complex conditions, the required test volume of testing at one failure accepting in the overall nonhomogeneous sample can be determined based on the Bernoulli’s binomial test (that was introduced to the test under similar conditions, when using a nonhomogeneous sample). There is no need to determine the probability of condition occurrences, values of the partial success probabilities; and their hypotheses are not tested. The paper proves that the Bernoulli’s binomial test scheme use allows minimizing the required total volume of testing under nonhomogeneous operating conditions, providing the required level of reliability about the decisions made.