Wyniki wyszukiwania - BazTech

1

Robot sensor failure detection system based on convolutional neural networks for calculation of Euler angles

Świetlicka A., Kolanowski K.

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2020

|

Vol. 68, nr 6

1525--1533

EN

In this work, we present a failure detection system in sensors of any robot. It is based on the k-fold cross-validation approach and built from N neural networks, where N is the number of signals read from sensors. Our tests were carried out using an unmanned aerial vehicle (UAV, quadrocopter), where signals were read from three sensors: accelerometer, magnetometer and gyroscope. Artificial neural network was used to determine Euler angles, based on signals from these sensors. The presented system is an extension of the system that we proposed in one of our previous papers. The improvement shown in this work took place on two levels. The first one was related to improvement of a neural network՚s reproduction quality – we have replaced a recurrent neural network with a convolutional one. The second level was associated with the improvement of the validation process, i.e. with adding some new criteria to check the values of Euler՚s angles determined by the convolutional neural network in subsequent time steps. To highlight the proposed system improvement we present a number of indicators such as RMSE, NRMSE and NDR (Normalized Detection Ratio).

2

Concept of AHRS algorithm designed for platform independent IMU attitude alignment

Tomaszewski D., Rapiński J., Pelc-Mieczkowska R.

Reports on Geodesy and Geoinformatics

|

2017

|

Vol. 104

33--47

EN

Nowadays, along with the advancement of technology one can notice the rapid development of various types of navigation systems. So far the most popular satellite navigation, is now supported by positioning results calculated with use of other measurement system. The method and manner of integration will depend directly on the destination of system being developed. To increase the frequency of readings and improve the operation of outdoor navigation systems, one will support satellite navigation systems (GPS, GLONASS ect.) with inertial navigation. Such method of navigation consists of several steps. The first stage is the determination of initial orientation of inertial measurement unit, called INS alignment. During this process, on the basis of acceleration and the angular velocity readings, values of Euler angles (pitch, roll, yaw) are calculated allowing for unambiguous orientation of the sensor coordinate system relative to external coordinate system. The following study presents the concept of AHRS (Attitude and heading reference system) algorithm, allowing to define the Euler angles.The study were conducted with the use of readings from low-cost MEMS cell phone sensors. Subsequently the results of the study were analyzed to determine the accuracy of featured algorithm. On the basis of performed experiments the legitimacy of developed algorithm was stated.

3

Determination of the orientation of an object within a 3D space. Implementation and example applications

Różanowski K., Lewandowski J., Placha M.

International Journal of Microelectronics and Computer Science

|

2015

|

Vol. 6, nr 4

124--129

EN

The article presents a design of a measurement system implementing algorithms for determination of the orientation of objects within three-dimensional space using am integrated triaxial MEMS system, magnetometer, and Madgwick’s AHRS sensor fusion algorithm. Also included in the proposed implementation are the algorithms for calibration of sensors. Estimated orientation of the object of interest is provided using Euler’s angles or quaternions The system consists of a data acquisition system and software to visualize the acquired data. The main components of the acquisition system include a microcontroller featuring ARM Cortex M4 processor core and integrated 9DOF module consisting of an accelerometer, gyroscope, and magnetometer. The measurement system is capable of communicating with other devices via a Bluetooth interface. The measurements of the monitored values read by 9DOF sensors may be collected at sampling frequencies of up to 100Hz. Options to save data to SD cards and to maintain power supply from a battery are also available. The proposed solution is characterized by low construction costs, small dimensions, and ease of implementation in all types of systems. It can be used for example in mapping the movement of limbs (spatial orientation of the foot, detection of gait cycle phases, assessment of motor activity), as a support tool in inertial navigation systems or in the control of objects in motion (aerial vessels, mechanical vehicles). The article also presents an application of the system as a limb motion capture device.

4

Diagnozowanie inercjalnych układów orientacji przestrzennej i nawigacji stosowanych w nahełmowych systemach celowniczych

Szelmanowski A.

TTS Technika Transportu Szynowego

|

2012

|

R. 19, nr 9

719--728, CD

PL

W artykule omówiono błędy czujników inercjalnych wykorzystywanych w systemach AHRS i INS (w zakresie prędkości kątowych i przyspieszeń liniowych) oraz ich wpływ na błędy wyliczanych parametrów pilotażowo-nawigacyjnych (takich jak kąty orientacji przestrzennej oraz prędkości liniowe i współrzędne pozycji nawigacyjnej) obrazowanych m.in. w nahełmowych systemach celowniczych. Przedstawiono problemy diagnozowania systemów nawigacji inercjalnej, zarówno tych najnowocześniejszych (np. centrali TOTEM-3000 z czujnikami laserowymi, integrowanych na bazie cyfrowej szyny danych MIL-1553B lub ARINC-429), jak i „starszych” rozwiązań konstrukcyjnych (np. układów IKW-8 stosowanych na samolotach Su-22). Podano metody badań torów przetwarzania sygnałów z czujników inercjalnych oraz wytyczne dla komputerowego systemu oceny stanu technicznego systemów nawigacji inercjalnej zaawansowanych eksploatacyjnie.

EN

The paper has been intended to discuss errors of inertial sensors used in Attitude Heading Reference and Inertial Navigation Systems (AHRS and INS, respectively) within the range of angular rates and linear accelerations, and how they affect errors in calculated flight parameters such as angles of rotation in three dimensions (aircraft orientation and control, i.e. aircraft flight attitude), linear velocities and co-ordinates of navigational position displayed on, among other items, the joint helmet-mounted cueing systems. Issues of the diagnosing the inertial navigation systems, both the most advanced ones (e.g. the TOTEM 3000 Inertial Reference System with laser sensors, integrated into the MIL-1553B or ARINC-429 based digital data bus system), and ones of older design (e.g. the IKW-8 systems used on the Su-22). Methods of examining lines to transmit inertial-sensors generated signals have been given. What follows is guidelines for a computer-based system to assess health/maintenance status of highly worn-and-torn inertial navigation systems.

5

Wykrywanie uszkodzeń układu odniesienia i kursu dla systemu pośredniego sterowania samolotem lekkim

Dołęga B., Kopecki G.

Pomiary Automatyka Kontrola

|

2005

|

R. 51, nr 9 bis

249--251

PL

Artykuł przedstawia zasadę działania układu odniesienia i kursu dla systemu pośredniego sterowania samolotem. Na jej podstawie przedstawione możliwości wykrywania uszkodzeń w oparciu o występującą redundancję sprzętową i analityczną. Przedstawiono metody wykrywania uszkodzeń z podziałem opartym o źródła użytych sygnałów wejściowych. Przedstawione wyniki oparte są o dane uzyskane w próbach w locie.

EN

The paper presents principles of operation of the attitude-heading reference system for fly-by wire control system for small aircraft. The system is being designed in Department of Control Systems and Avionics of the Rzeszów University of Technology. There are presented possibilities of fault detection and isolation based on hardware and analytical redundancy. Different fault detection methods classified by input signals sources are presented. Presented simulation results are based on flight tests data.