Most adjustable-speed AC drive systems are constructed in such a way that one motor receives power from one inverter and uses vector control as the basic control principle. However, in some cases there is a need to power several motors in parallel from a single inverter, that minimizes the size, weight and cost of such a system. The most common examples of such systems are rail and urban electric vehicles, where two to four induction motors are connected to drive in parallel. Control of such a system is a difficult task, especially in conditions of unbalanced loads on the motors, that can occur in conditions of different adhesion of wheels with rails. The inability to provide individual control of the motor when powered by a single inverter can lead to a decrease in the safety level of such a vehicle due to the loss of stability when changing the current value of the adhesion coefficient of individual wheel pairs. Mechanical processes in the traction system are analyzed, in which each wheel pair is driven by a separate motor powered by a common inverter. It is shown that the identity of the values of the adhesion coefficients is an important condition for the stability of such a system, that cannot be guaranteed in the actual practice of the operation of the vehicle. Therefore, the development and research of control systems that are capable of operating the system in a variety of rail / road conditions is an important direction for the further development of such systems. The structure of mathematical model of traction electromechanical system consisting of two induction motors powered by one inverter is proposed. The adjustable-speed control is based on the scalar control system, that is the easiest to implement because it does not require the estimation of the state variables of the system components. Sinusoidal pulse width modulation is selected as the switch control signal method. Operation of traction electromechanical system with scalar frequency control law is investigated by mathematical modeling. It has been proven that changing the characteristics of a single wheel pair's adhesion can lead to a loss of stability by a system that is unacceptable in terms of providing a comfortable and safe operation of the vehicle. Keywords: traction electric drive, scalar control, adhesion, mathematical model, frequency control
The SMALT software package (Statistical methods of analysis of literary texts) is implemented to conduct research in the field of attribution of literary texts. The article discusses new tools for storing, visualizing, comparing and searching data implemented in the system. They are implemented for text analysis using graph-theoretic models. Examples of philological studies performed using these tools are given.
In multifactorial systems using textual and graphical information in matrix factorization to facilitate the problem of separate data processing. Recently, in some studies, the study of neural networks to understand the content of text and graphic elements more deeply and to achieve efficacy by creating more accurate patterns of recognition of elements. However, the open question remains about how to effectively use graphic data from the thermal imager in matrix factorization. In this paper, we proposed a double-regularized matrix factorization with deep neural networks (DRMF) to solve this problem. DRMF applies a multilayered neural network model by stacking a convolutional neural network and a secured repetitive neural network to create independent distributed views of user content and objects. Then representations serve to regularize the generation of hidden models for both users and for elements of matrix factorization. So the proposed new model of the neural network works better than a model with a single convergent neural network. In this paper, we propose double - regularized matrix factorization with deep neural networks (DRMF) to solve this problem. DRMF uses a multi-layered neural network model by enclosing a convoluted neural network and a secure repeating neural network to create independent distributed representations of user content and objects. Then the representations are used to regularize the generation of hidden models for both users and elements of matrix factorization. Thus, the proposed new neural network model works better than the model with a single converging neural network. In traditional SF methods, only a feedback matrix is used, which contains explicit (eg, estimates) or implicit feedback to train and predict the life of the motor. As a rule, the feedback matrix is liquid, which means that most users encounter several elements. Based on this was presented in Proc. BigData Congress. However, this view has been significantly expanded using a new deep neural network model and adding new experimental attachments compared to the conference publication.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.