articles
| The article discusses issues related to the development of a flexible intelligent software package for solving the problem of optimal planning of multi-assortment production. These industries are characterized by a large range of products, many types and configurations of equipment, with an increase in the dimension of the problem, the number of options for production schedules grows exponentially, therefore, it is extremely important to develop a specialized complex for effective optimal planning and scheduling, insisting on the characteristics of various multi-assortment industries. The purpose of this work is to increase the productivity of multi-assortment enterprises and reduce the time of production of products by developing methods and algorithms for optimizing scheduling in the form of a problem-oriented software package. The article presents a mathematical formulation of the optimization problem and a set of mathematical models and algorithms for the formation of objective functions for optimal scheduling of reconfigurable productions. Conducting this study is based on the use of methods of scheduling theory, optimization and evolutionary calculations, tools for object-oriented development of complex software systems and databases. The proposed software package has various intelligent user interfaces, supplemented by databases of products, equipment and technological regulations, a library of objective functions and mathematical optimization methods, an expert system tuning module, as well as an interactive system for visualizing the resulting production plans in the form of a Gantt chart and decision tree of the optimization problem. Testing of the software package was carried out on the data of polymer and metallurgical enterprises in Russia and Germany and confirmed the effectiveness of solving planning problems. Implementation of the proposed software package makes it possible to ensure efficient loading of enterprise equipment, reduce production costs and simplify the process of making managerial decisions in the course of production planning. Continue... | |
|
№ 5(101)
21 october 2022 year
Rubric: Models and methods Authors: Dli M. I., Rysina (Lobaneva) E., Sinyavsky Y., Vasilkova M. |
The paper presents the results of research aimed at developing a method and software tools for identifying the class of a mixing device by its resistance coefficient through experimental data processing. Currently, the main methods for studying mixing devices are finite element methods, as well as procedures of estimating turbulent transfer parameters using laser dopplerometry and chemical methods of sample analysis. These methods require expensive equipment and provide results only for certain types of equipment. This makes it difficult to extend the inferences to a wider class of devices with different designs of mixing impellers. The proposed method involves processing the results of an experiment in which a point light source forming a beam directed vertically upwards is located at the bottom of a container filled with a transparent liquid. A mixing device with variable rotation frequency is placed in the container. When performing experiments in real conditions, small deviations in the size and location of the mixing device lead to difficult-to-predict fluctuations of the funnel surface. Therefore, the image of one marker describes a trajectory that is difficult to predict. It, under certain conditions, can intersect with the trajectories of other markers or be interrupted at the moment when the marker is closed by a stirrer blade passing over it. The resulting image of the markers is associated with a change in the rotational speed of the blade by a rather complex relationship. To identify this dependence, it is proposed to use deep neural networks operating in parallel in two channels. Each channel analyzes the video signal from the surface of the stirred liquid and the time sequence characterizing the change in the speed of rotation of the blades of the device. It is proposed to use neural networks of various architectures in the channels - a convolutional neural network in one channel and a recurrent one in another. The results of the operation of each data processing channel are aggregated according to the majority rule. The computational novelty of the proposed algorithm lies in the expansion of the receptive field for each of the networks due to the mutual conversion of images and time sequences. As a result, each of the networks is trained on a larger amount of data in order to identify hidden regularities. The effectiveness of the method is confirmed by testing it with the use of a software application developed in the MatLab environment. Continue... |
|
Neural network analysis method of heat treatment processes of pelletized phosphate ore raw materials
№ 5(101)
21 october 2022 year
Rubric: Models and methods Authors: Puchkov A., Fedotov V., Sokolov A. M. |
Currently, there is an acute problem of waste disposal of mining and processing plants, which accumulate in significant volumes in the territories adjacent to them and pose a serious threat to the environment. In this regard, the creation of technological systems for processing ore waste and the improvement of their information support represent an urgent area of research. An example of such a system is a complex chemical and energy technology system for the production of yellow phosphorus from waste apatite-nepheline ores. The purpose of the study was to develop a model for collecting data on the parameters of the processes of heat treatment of pelletized phosphate ore raw materials in such a system, as well as a method for identifying dependencies between these parameters. The identification of dependencies in the information support of the yellow phosphorus production system will improve the quality of its functioning in terms of management criteria, energy and resource efficiency. To achieve this goal, the tasks of choosing a mathematical concept for the basis of the method being developed, constructing an algorithm and creating software implementing this method, conducting model experiments were solved. The method is based on the use of deep recurrent neural networks of long-term short-term memory, which have a high generalizing ability and are used in solving problems of regression and classification of multidimensional time sequences, in the form of which, as a rule, the parameters of a chemical and energy technology system are presented. The method is implemented as an application created in the MatLab 2021 environment. The application interface allows you to interactively conduct experiments with various sets of input and output parameters to identify the relationship between them, as well as change the hyperparameters of neural networks. As a result of the application, a repository of trained neural networks is created that simulate the relationships found between the specified parameters of the technological system and can be applied in decision support systems, management and engineering. Continue... |
| Industry 4.0 is an initiative that involves building smart factories, supply chains and the production process. One of the key related concepts is digital twins, which enable forecasting and planning using real-time data in complex models. The concept involves working with large amounts of data, both when developing systems from scratch, and for building them on the basis of existing modeling software. The tasks of processing, storing and using such data streams are solved daily by large Internet companies operating on the data of millions of users to build business processes. Such companies have been developing systems using microservice architecture for ten or more years, which allows them to build scalable and deterministic systems for processing data flow. However, within the framework of the task, it became necessary to use modeling programs to build a digital twin, which set us the task of integration, since programs for building models are not adapted to work within microservice systems. The way out of this situation is to create data exchange drivers. An example of such a simulation program is Unisim Design. The paper formulates the problem of extracting data from a program that was not originally adapted to work within a software package that implies constant interaction between its parts. A solution has been found and implemented that allows obtaining data from this program without using commercial software and closed libraries. Continue... | |
|
№ 5(101)
21 october 2022 year
Rubric: Defense software Authors: Zainchkovsky A., Lazarev A., Sinyavskiy V. |
Currently information exchange methods and means of communication development are being done a significant impact on the level of all industrial and economic entities innovation potential, which is also the same for their group formations, such as regional complexes. It is necessary to note high degree of integration and interdependence of all such systems elements and processes closely interconnected by different kind of networks. Among them, it is possible to highlight the interaction between participants of scientific and industrial cluster within the framework of innovative activities, which should provide possibility to transfer and receive various kinds of data, which could be both open and confidential type. At the current stage, there is not many applied tools for ensuring confidentiality in the implementation of these processes. For example, they partially solve the problem of traffic tunnelling systems based on OpenVPN or WireGuard tunnels, and other software solutions provide the potential of an extensible cloud (Nextcloud). However, analysing the functionality of these solutions, it is possible to identify shortcomings that do not allow their implementation in the complex production and economic systems processes of innovative development. Thus, existing traffic tunnelling solutions are not adapted for deployment on a corporate scale with a flexible organisational structure. In solutions based on Nextcloud, the complexity disadvantages of the server configuration and the cost of the primary software configuration are highlighted. To solve the above problems, in article has been proposed an intelligent traffic tunneling system, which is based on using additional means of primary automated OpenVPN connection initialization at neural module expense. A dynamic digital fingerprint distribution system with two-way key exchange was used as an authorization server. The developed software solution was tested and then compared with existing analogues. This experiment may to conclusion that the developed software solution is not inferior in a number of aspects to existing methods, and can subsequently be used to ensure secure information and communication exchange between industrial and economic entities in clusters during innovative processes implementation. Continue... |
|
№ 5(101)
21 october 2022 year
Rubric: Processes and systems modeling Authors: Chumakova E., Gasparian M., Korneev D. |
The paper discusses the issues of implementing an adaptive testing system based on the use of artificial neural network (INS) modules, which should solve the problem of intelligent choice of the next question, forming an individual testing trajectory. The aim of the work is to increase the accuracy of the INS to form the level of complexity of the next test question for two types of architectures – direct propagation (FNN – Feedforward Neural Network) and recurrent with long-term short-term memory (LSTM – Long-Short Term Memory). The data affecting the quality of training are analyzed, the architectures of the input layer of the direct propagation INS are considered, which have significantly improved the quality of neural networks. To solve the problem of choosing the thematic block of the question, a hybrid module structure is proposed, including the INS itself and a software module for algorithmic processing of the results obtained from the INS. A study of the feasibility of using direct propagation ANNs in comparison with the LSTM architecture was carried out, the input parameters of the network were identified, various architectures and parameters of the ANN training were compared (algorithms for updating weights, loss functions, the number of training epochs, packet sizes). The substantiation of the choice of a direct distribution network in the structure of the hybrid module for selecting a thematic block is given. The above results were obtained using the Keras high-level library, which allows you to quickly start at the initial stages of research and get the first results. Traditionally, learning has taken place over a large number of eras. Continue... |
