+7 (495) 987 43 74 ext. 3304
Join us -              
Рус   |   Eng

Authors

Maksimkin Maksim V.

Degree
Cand. Sci. (Econ.), Associate Professor, Senior Researcher, Information Technologies in Economics and Management Department, Branch of the National Research University “MPEI” in Smolensk
E-mail
mmaximkin@yandex.ru
Location
Smolensk, Russia
Articles

Software model of an intelligent control system for complex processes of small-scale ore processing

Intelligent process control systems allow analyzing incoming information about the control object and the external environment at a qualitatively new level and, on this basis, increasing the efficiency of the entire production. The article presents the results of a study aimed at developing a software model of an intelligent control system for complex processes of small-scale ore processing. The complexity of the processes lies in the interrelationship of many variables describing the technological units involved in processing. An analytical description of such interrelations allows describing processes with high accuracy, but leads to complex calculations that are difficult to apply in real conditions. The use of new computational algorithms from the group of intelligent methods made it possible to overcome this contradiction, ensuring, on the one hand, good accuracy of solutions, and on the other hand, making it possible to automate the adjustment of the control system to changing input effects and external conditions. The basis of the proposed software model is a deep neural network of long short-term memory, solving the regression problem when analyzing input data and calculating control effects. The novelty of the research results is the structure of the software model of the intelligent control system, including a neural network as a regulator and a hierarchical system of fuzzy inference for a generalized assessment of the control qualities. An original feature of the software structure is the use of a calculator of derivatives of different orders to feed them to the input of the neural network, which helps to expand its receptive field and increases the accuracy of its results. Testing of the proposed structure of the software model was carried out in the MatLab-Simulink environment. The results of the simulation experiment showed that, unlike the PID controller, the use of a deep neural network as a regulator allows for successful compensation of the influence of external factors on the quality of control. Read more...

Model for assessing energy and resource efficiency of process recycling small-ore raw material based on a tree of fuzzy inference systems

The article presents a software model of complex processes of small-scale ore raw material processing based on a trainable tree of fuzzy logical inference systems. Processing of such raw materials not only provides a valuable end product, such as yellow phosphorus, but also helps to solve the problem of ore waste disposal, the fine fractions of which create significant environmental damage to the territories adjacent to mining and processing plants. The technological system of small-scale ore raw material processing consists of energy-intensive units, so even a slight relative reduction in resource and energy costs leads to large savings in absolute figures. Such a reduction can be achieved by optimizing the control of units, the synthesis of which requires the availability of process models, so improving the methods and tools for modeling is an urgent research task. A feature of the proposed model is that its inputs are not only variables describing resource transformations, but also variables reflecting the energy costs of individual technological units. This allows using the model to calculate the energy and resource efficiency of small-scale ore raw material processing. The hierarchical structure of the fuzzy-logical tree is capable of reflecting the interrelationship of processes of various natures accompanying the processing of small-scale raw materials, and also contributes to increasing the efficiency of its training by dividing the feature space of large dimension into several groups on which individual tree nodes are trained. The program developed in the MatLab environment and implementing the proposed model showed high regression accuracy on a synthetic set of input data, which may indicate the feasibility of using the proposed model in problems of optimizing control systems for processing small-scale raw materials according to the criterion of energy and resource efficiency. Read more...