Recurrent network as a tool for calibration in automated systems and interactive simulators

Abstract

<p>We have constructed a method for the auto-calibration and correction of values of the vector of magnetic induction, which is suitable for use under conditions of limited computational resources in microcontrollers and SoC System-on-a-Chip. The efficiency of the system in general was investigated experimentally by using an additional board, which holds six pairwise connected primary Hall sensors. Correctness of work of the algorithm was checked at the designed and fabricated microprocessor test module, the prototype of which was the most simplified variant of the popular microcontroller board Arduino. We have implemented the structure of a recurrent network that is built based on vectors-indicators and recurrent decomposition; and examined the efficiency of algorithms for the calibration and processing of peripheral information. The microprocessor module was designed and manufactured, using which we studied dependence of the magnitude of measurement error on the properties of the sensor and hardware features for the automated systems and interactive simulators. A principle of the modular structure of software was employed, which increases the percentage of reuse of software parts by the organization of requests, as well as makes it possible to create new functions without making significant changes to the existing code. To ensure the independence of software from the hardware platform of sensor realization and the system of data processing and transfer, it is equipped with a module that adapts the level of hardware abstraction. The result of its implementation is the simplified procedure for software deployment in other hardware means. All platform-dependent system functions are implemented at this level. Independence from the hardware features of platforms is provided by engaging the computational tools, techniques, tools and modules of SPI, UART interfaces, and Modbus-RTU protocol. They help configure and exchange data with peripheral devices for its further processing by a personal computer.</p>

Authors and Affiliations

Alexander Trunov

Keywords

Related Articles

An algebraic method for calculating PageRank

<p>An algebraic method is proposed for finding PageRank estimates for pages of websites. The amount of calculation in the proposed method does not depend on the value of the damping coefficient, which allows obtaining mo...

Efficiency analysis of the technology of roller formation of finely-grained concrete products

<p><span style="font-family: 'Times New Roman'; font-size: small;">Efficiency of using the roller forming technology with forced rotation of the working body (roller or sector) was disclosed. The results of development o...

Development of an integration­analytical method for the initiation of construction projects of industrial objects

<p class="a"><span lang="EN-US">We studied management processes of initiation of industrial projects. We considered the specific features of industrial objects construction projects that affect a structure of a project l...

A method of designing of torque­-flow pump impeller with curvilinear blade profile

<p>The research is devoted to energy efficiency increasing of a “Turo” type torque-flow pump by improving its impeller. This allows minimizing the total pump installation life cycle cost as a result of reducing the costs...

Design of fire-resistant heat- and soundproofing wood wool panels

<p>The conducted research revealed the possibility to manufacture heat- and soundproofing materials for the arrangement of buildings. Wood fibers, which are produced in the form of flat panels, are the raw materials for...

Download PDF file
  • EP ID EP527918
  • DOI 10.15587/1729-4061.2018.126498
  • Views 61
  • Downloads 0

How To Cite

Alexander Trunov (2018). Recurrent network as a tool for calibration in automated systems and interactive simulators. Восточно-Европейский журнал передовых технологий, 2(9), 54-60. https://europub.co.uk./articles/-A-527918