Wyniki wyszukiwania - BazTech

1

Artificial neural network model for estimation of relative airplane altitude

Tomiło Paweł, Michałowska Joanna, Laskowski Jan, Pytka Jarosław, Kochan Orest, Gnapowski Ernest

Przegląd Elektrotechniczny

|

2025

|

R. 101, nr 2

116--119

EN

The main purpose of the publication is to develop an artificial neural network model capable of estimating aircraft altitude based on accelerometer and gyroscope readings. The developed network structure uses LSTM, SE and transform encoder layers. Measurement data for training, validation and testing of the neural network were obtained from tests using an original measurement system developed. The developed device set was placed on the Koliber 150 aircraft. In order to verify the correctness of the model, the values estimated by the model were compared with those estimated by the Kalman filter algorithm using the double integration algorithm. The developed artificial neural network model has an overall estimation error of 7.43m, while the error for the Kalman filter was 20.27m. It has been shown that the use of the proposed model allows achieving satisfactory accuracy in aircraft altitude estimation due to the model's ability to adapt to the drift in the Inertial Measurement Unit (IMU).

PL

Głównym celem publikacji jest opracowanie modelu sztucznej sieci neuronowej, który będzie w stanie oszacować wysokość samolotu na podstawie wskazań akcelerometru i żyroskopu. Opracowana struktura sieci wykorzystuje warstwy LSTM, SE i enkodera transformatorowego. Dane pomiarowe do uczenia, walidacji i testowania sieci neuronowej uzyskano z badan za pomocą opracowanego autorskiego system pomiarowego. Opracowane urządzenie umieszczono na samolocie Koliber 150. W celu weryfikacji poprawności modelu wartości oszacowane zostały porównane z wartościami, które oszacowano na podstawie algorytmu filtrem Kalmana z zastosowaniem algorytmu podwójnego całkowania. Opracowany model sztucznej sieci neuronowej charakteryzuje się ogólnym błędem estymacji wynoszącym 7.43m, zaś błąd dla filtru Kalmana wyniósł 20.27m. Wykazano że zastosowanie zaproponowanego modelu pozwala na osiągnięcie zadowalającej dokładności przy estymacji wysokości samolotu dzięki zdolności modelu do adaptacji do dryftu w Inercyjnej jednostce pomiarowej (IMU).

2

Using a long short-term memory model to predict force values of Taekwon-do turning based on spatio-temporal parameters

Mosler Dariusz, Błażkiewicz Michalina, Góra Tomasz, Bednarczuk Grzegorz, Wąsik Jacek

Acta of Bioengineering and Biomechanics

|

2025

|

Vol. 27, no. 1

83--92

EN

The aim of this study was to investigate the feasibility of using Long Short-Term Memory (LSTM) neural networks to predict Taekwondo kick force from data obtained by inertial measurement unit (IMU) sensors, providing a cost-effective alternative to traditional force plates in sports biomechanics. Methods: IMU (Noraxon Ultium) data from 13 International Taekwon-do Federation (ITF) athletes (9 training, 4 validation) across genders and skill levels (expert in training, expert/advanced in validation) were collected. Sensors were attached to a foot, shank and tight of kicking leg. Athletes performed turning kicks in diverse stances towards a padded force plate (2000 Hz) attached to a wall. LSTM models were trained to predict kick force value, and trained on capturing the IMU data from sensors placed on the lower limb. Results: The trained LSTM models showed accuracy on the training data (R2 values in the range of 0.972–0.978). Feature validity analysis highlighted the importance of ankle dorsiflexion in shaping the model score. Model performance on the validation dataset was less consistent, ranging from good accuracy (RMSE 6.91) to poor accuracy (RMSE over 30), depending on the participant tested. Conclusions: This study demonstrated the potential of LSTM models combined with IMU data to predict Taekwondo kick forces. Although the validation performance indicated the need for further model refinement or the inclusion of additional input variables, the results highlighted the feasibility of predicting force values without relying on a force plate. This approach could enhance the accessibility of field studies conducted outside laboratory settings.

3

Displacement measurement system for small-scale vessels berthed in physical models of port terminals

de Oliveira Bezerr R., de Melo Bernardino J. C.

TransNav : International Journal on Marine Navigation and Safety of Sea Transportation

|

2024

|

Vol. 18 No. 1

169--175

EN

This paper presents the development of a displacement measurement system for small-scale physical models of moored ships, aimed at providing data to evaluate displacement amplitudes and determine whether they surpass predetermined operational limits. The system, which combines cameras and inertial sensors, captures six degrees of freedom, allowing measurements of surge, sway, heave, yaw, roll, and pitch. The developed system was initially tested isolating each degree of freedom for analysis, and subsequently applied to a scale model of a port terminal berth, with a bulk carrier vessel docked, subject to wave action. Scale models of port terminals have been extensively validated over numerous years of research and development. To evaluate the system's response, displacement measurements obtained through the developed system were compared with a commercial system widely recognized for measuring rigid body movements, the Qualisys® system. This comparison shows both systems obtained similar results, indicating that the developed system meets its intended purpose. Overall, the system provides a reliable tool for studying the complex behavior of moored vessels and evaluating operational and safety conditions in port terminals.

4

Spectral analysis of compass errors based on fast fourier transform and reduction absolute errors using a pass-band finite impulse response filter

Jaskólski Krzysztof, Czaplinski Wojciech, Tomczak Arkadiusz

Polish Maritime Research

|

2024

|

nr 2

109--120

EN

Compass errors can be regarded as a deviation of the vessel from the expected heading. Gyrocompass errors are randomly oscillating in nature, and it is difficult to describe the behaviour of a gyrocompass sufficiently accurately using mathematical relationships. Fibre-optic gyroscopes have no mechanical components, so the variability in their indications has a different nature; the computational processes and inertial sensors used cause certain types of errors. Thus far, compass studies have focused on presenting absolute errors in the time domain. However, compasses exhibit specific characteristics in the frequency domain that affect the amplitude of their deviation. This leads to the issue of identifying the oscillatory spectrum of errors in the operation of such compasses, and how this spectrum is impacted by the dynamic movement of the vessel. We attempt to assess this phenomenon by means of measurements taken on board the training and research vessel M/S NAWIGATOR XXI. The application of a fast Fourier transform allows for calculation of the absolute compass errors in the frequency domain, meaning that the frequency of occurrence of errors can be observed as noise against the background of the useful signal. Our results confirm the value of applying a finite impulse response filter, which is used to filter out noise in the form of absolute compass errors from the useful signal background. The convolution function proposed here considerably extends the possibilities for analysing the signal spectrum in the frequency domain when testing for the accuracy of compass device indications, and enables the elimination of random errors with a low frequency of occurrence.

5

Enhanced green logistics: sustainable distribution and warehousing with IMU positioning

Wu Xiangfeng

Ecological Chemistry and Engineering. S

|

2024

|

Vol. 31, nr 2

225--241

EN

The objective of the green logistics distribution model is to minimise environmental pollution and energy usage by employing clean energy, optimising transport routes and enhancing transport efficiency. Nonetheless, current studies on green logistics distribution models and warehousing planning exhibit certain drawback, such as imprecise location accuracy and decreased distribution revenues. To overcome these challenges, this paper proposes a novel approach that combines inertial measurement unit (IMU) and binocular vision, leveraging multisource information positioning. Specifically, the method integrates data collection and preprocessing modules to gather crucial logistics distribution task information, encompassing IMU data, image data and vehicle data. The visual and inertial positioning module consists of two components: visual positioning based on the grey centre method and IMU positioning based on the integral essence. Finally, an adaptive Kalman filter is employed to merge the results of visual positioning and IMU positioning, thus producing the ultimate logistics vehicle positioning result. The proposed method effectively addresses existing challenges in the green logistics distribution model and warehouse planning. In particular, the experimental results demonstrate that the algorithm proposed in this study reduces the location error by 8%. Furthermore, logistics and distribution costs are reduced by 11%, contributing to the promotion of sustainable and environmentally friendly logistics operations.

6

Can data processing algorithms ensure sufficient accuracy to estimate human body pose via wearable systems with use of IMU sensors? – an experimental evaluation

Szczerba Aleksandra, Prochor Piotr, Piszczatowski Szczepan

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2024

|

Vol. 72, nr 1

art. no. e148835

EN

Background: The aim of the study was to answer two questions: 1 – Can data processing algorithms ensure sufficient accuracy for estimating human body pose via wearable systems? 2 – How to process the IMU sensor data to obtain the most accurate information on the human body pose? To answer these questions, the authors evaluated proposed algorithms in terms of accuracy and reliability. Methodology: data acquisition was performed with tested IMU sensors system mounted onto a Biodex System device. Research included pendulum movement with seven angular velocities (10-120°/s) in five angular movement ranges (30-120°). Algorithms used data from accelerometers and gyroscopes and considered complementary and/or Kalman filters with adjusted parameters. Moreover, angular velocity registration quality was also taken into consideration. Results: differences between means for angular velocity were 0.55÷1.05°/s and 1.76÷3.11%. In the case of angular position relative error of means was 4.77÷10.84%, relative error of extreme values was 2.15÷4.81% and Spearman’s correlation coefficient was 0.74÷0.89. Conclusions: Algorithm calculating angles based on acceleration-derived quaternions and with implementation of Kalman filter was the most accurate for data processing and can be adapted for future work with IMU sensors systems, especially in wearable devices that are designated to support human in daily activity.

7

Analysis of micro-electromechanical inertial measurement units for unmanned aerial vehicle applications

Mammadov Aftandil

Zeszyty Naukowe. Transport / Politechnika Śląska

|

2022

|

z. 117

129--138

EN

Typically, an inertial navigation system (INS) is used to determine the position, speed, and orientation of an object moving relative to the earth's surface. The navigation information (position, speed and orientation) of an unmanned aerial vehicle (UAV) is needed to control its flight. Since the resistance of INS to interferences is very high, it is possible to ensure reliable flights in conditions of high-intensity noise. This article explores the principles of constructing inertial measurement units (IMU) that are part of the INS and indicates perspective directions for their development. Micro-electromechanical inertial measurement units were studied in this work, and functional and principal electrical circuits for connecting units of inertial measurements to the microcontroller were developed. The results of practical measurements of units without calibration and after calibration were obtained using the created laboratory device. Based on the obtained results, the necessity of sensor calibration was revealed, and accuracy was improved by performing calibration with the Kalman filter algorithm. The Kalman filter is the heart of the navigation system. In a low-cost system, IMU errors like bias, scale factor error and random walk noise dominate the INS error growth.

8

Comparison of the optoelectronic BTS Smart system and IMU-based MyoMotion system for the assessment of gait variables

Bartoszek Amadeusz, Struzik Artur, Jaroszczuk Sebastian, Woźniewski Marek, Pietraszewski Bogdan

Acta of Bioengineering and Biomechanics

|

2022

|

Vol. 24, no. 1

104--116

EN

Although inertial measurement unit (IMU)-based systems have been validated against optoelectronic systems for recording joint kinematics, the accuracy of each system must be evaluated, and measurements from different systems cannot be easily compared. Therefore, this study compared the joint angles recorded using the IMU-based MyoMotion system and the optoelectronic BTS Smart-DX 700 system during Nordic walking. Methods: The study subject, a long-time Nordic walking instructor, was assigned to walk 12 m/trial (14 trials with 5 sampled gait cycles) at a velocity preferred for Nordic walking. The trials were simultaneously recorded by both systems. The instantaneous lower (ankle, knee, hip) and upper (shoulder, elbow, wrist) limb joint angles were recorded. Results: The joint angles from MyoMotion were significantly larger or smaller (depending on the joint and plane) than those from BTS. Conclusions: Joint angles measured by MyoMotion are not interchangeable with values from BTS, and IMU-recorded values should be interpreted carefully. However, MyoMotion can still provide information about intra-individual changes based on the joint angle profiles, e.g., following Nordic walking training.

9

A kinematic model of a humanoid lower limb exoskeleton with pneumatic actuators

Głowiński Sebastian, Ptak Mariusz

Acta of Bioengineering and Biomechanics

|

2022

|

Vol. 24, no. 1

145--157

EN

Although it is well-established that exoskeletons as robots attached to the human body's extremities increase their strength, limited studies presented a computer and mathematical model of a human leg pneumatic exoskeleton based on anthropometric data. Methods: By using Inertial Measurement Units a lower limb joint angles (hip, knee and ankle in sagittal plane) during walking and running were calculated. The geometric model of a human leg pneumatic exoskeleton was presented. Joint angle data acquired during experiments were used in the mathematical model. Results: The position and velocity of exoskeleton actuators in each phase of the movement were calculated using the MATLAB package (Matlab_R2017b, The MathWorks Company, Novi, MI, USA). Conclusions: The obtained results demonstrate the efficiency of the proposed approach that can be utilized to analyze the kinematics of pneumatic exoskeletons using the dedicated design process. The developed mathematical model makes it possible to determine the position of lower limb segments and exoskeleton elements. The proposed model allows for calculating the position of the human leg and actuators' characteristic points.

10

The wavelet as the evaluation tool of vehicles’ seat suspension system

Glowinski Sebastian, Blazejewski Andrzej

Vibrations in Physical Systems

|

2020

|

Vol. 31, nr 2

art. no. 2020206

EN

In this paper, an innovative active seat suspension system for vehicles is presented. This seat suspension prototype is built with a shear guidance mechanism, an air spring, a hydraulic shock absorber and end-stop buffers. The acceleration particular signals are measured by using Inertial Measurement Units (IMUs) placed on the seat and the human head. As the excitation, the horizontal vibrations are applied. As an alternative to the classical Fourier approach, the Wavelet Transfer Function (WTF) is introduced to describe the effectiveness of particular seat suspension. In both of the system cases, the human head reaction is investigated by using the Matlab package.

11

Coupling of inertial measurement units with a virtual world model for supporting navigation in bronchoscopy

Michalski Dariusz, Nabagło Tomasz, Tabor Zbisław

Biocybernetics and Biomedical Engineering

|

2019

|

Vol. 39, no. 2

273--281

EN

Background and objective: The purpose of this paper is to provide a method for supporting navigation in bronchoscopy based on measurements of absolute orientation of a tip of a bronchoscope and the length a bronchoscope is pushed in the lumen of an examined bronchial structure. Methods: A hardware solution is designed and developed for collecting the data related to the absolute orientation of a tip of a bronchoscope and the length a bronchoscope is pushed in the lumen of an examined structure. A software which processes these data and visualizes in real-time the actual location of a bronchoscope tip in the lumen of a digital model of the examined structure (i.e. virtual bronchoscopy) is also designed and implemented. Results: A calibration procedure is developed which constitutes a basis for the operation of the proposed system. A phantom of a tree-like structure is build, imitating the anatomy of a bronchial tree, and the proposed method of navigation is tested for the task of navigating in the lumen of the phantom to user-selected target locations. Conclusion: A method has been proposed and tested for Inertial Measurement Unit (IMU)- based support of navigation in bronchoscopy.

12

Quantification of motor abilities during the execution of judo techniques

Frassinelli Stefano, Niccolai Alessandro, Zich Riccardo E., Rosso Valeria, Gastaldi Laura

Acta of Bioengineering and Biomechanics

|

2019

|

Vol. 21, no. 3

3--12

XX

Quantitative performance analysis is of great importance, especially to increase personalized training and to reduce injuries. The use of inertial sensors has given many possibilities and has been largely used in analysing technical capabilities of athletes. With respect to combat sports, judo has many issues resulting from the great number of variables involved in the techniques and due to the critical measurement environment. The aim of this study was to propose a method for measuring and quantifying motor abilities objectively. Methods: Four inertial sensors were fixed to the lower limbs and one on the sternum of five male and five female elite judo athletes. Accelerations and angular velocities of the lower limbs were measured in 480 judo techniques. Regression lines of accelerations and angular velocities have been analysed to obtain 5 single technique indices and 1 overall technique index representing the motor abilities connected, respectively to force expressions and coordination capabilities. Results: Correlations of motor abilities (force expression and coordination capabilities) and athletes’ weight and height were found in only 6.7% of pairs. Results of force expression and coordination capabilities for most of the athletes are in line with their level of technical and combat experience. Conclusions: This method allowed to “photograph” athlete’s technical level and to compare it in time through subsequent trials. With this innovative way, motor abilities could become evaluable and measurable, highlighting the importance of their objective quantification in order to evaluate effectiveness and efficiency of the sport technique.

13

Efficiency of MEMS inertial sensors used in low-dynamics application

Szumski A., Eissfeller B.

TransNav : International Journal on Marine Navigation and Safety of Sea Transportation

|

2017

|

Vol. 11, no. 2

221--226

EN

The analysis presents the performance of navigation application driven with MEMS and FOG inertial sensors. The inertial sensors were working under conditions simulating a potential robotic mission, which reduce accuracy of some of the navigation applications. Empirical results of the test confirm degradation of the navigation system performance in the presented demanding mission. Influence of the testing conditions and of the inertial sensor technology is presented and discussed in the paper.

14

Projekt mobilnego robota holonomicznego z bezprzewodowym inercyjnym systemem sterowania

Rychlik P., Kaczmarek W.

Mechanik

|

2017

|

R. 90, nr 7

634--636

PL

W artykule przedstawiono projekt mobilnego robota holonomicznego, przy czym szczególną uwagę zwrócono na jego sterowanie. Omówiono sposób przetwarzania wartości z czujnika inercyjnego na sygnały elementów wykonawczych, tworzących wraz z kołami szwedzkimi zdefiniowany wcześniej układ holonomiczny. W celu określenia poprawności funkcjonowania robota przeprowadzono szereg testów obejmujących jego oprogramowanie, a następnie wyznaczono podstawowe parametry charakteryzujące mobilność robota.

EN

The article presents the design of mobile holonomic robot, where special attention was given to the robot’s control method. It discusses the way of processing values from an inertial measurement unit to actuator signals. In order to determine the correct functioning of the robot, a number of tests were carried out covering its software, and followed by the determining of basic parameters characterizing robot’s mobility.

15

Estimation of Flight Path Deviations for SAR Radar Installed on UAV

Łabowski M., Kaniewski P., Konatowski S.

Metrology and Measurement Systems

|

2016

|

Vol. 23, nr 3

383--391

EN

The paper presents a method of calculation of position deviations from a theoretical, nominally rectilinear trajectory for a SAR imaging system installed on board of UAV. The UAV on-board system consists of a radar sensor, an antenna system, a SAR processor and a navigation system. The main task of the navigation part is to determine the vector of differences between the theoretical and the measured trajectories of UAV center of gravity. The paper includes chosen results of experiments obtained during ground and flight tests.

16

Projekt dwukołowego samobalansującego pojazdu

Ciężkowski M., Mystkowski A.

Przegląd Elektrotechniczny

|

2015

|

R. 91, nr 2

147-152

PL

Artykuł zawiera opis budowy dwukołowego samobalansującego pojazdu. Zostały w nim omówione główne części pojazdu oraz sposoby wyznaczenia, interesujących z punktu widzenia projektu, własności podzespołów użytych w budowie pojazdu. Poza opisem części sprzętowej została również omówiona część projektu związana z oprogramowaniem mikrokontrolerów wykorzystywanych przez pojazd. Dodatkowo przedstawiono sposób obliczania najważniejszych parametrów pojazdu. Wyniki obliczeń zostały zweryfikowane eksperymentalnie.

EN

The article describes the design and construction of two-wheeled self-balancing vehicle. The main parts of the vehicle and the designation methods of properties of the components used in the construction of the vehicle were discussed. In addition to describing the hardware part, the part of the project related to software used by the vehicle microcontrollers has also been discussed. Also, manner of calculations of important parameters of the vehicle was presented. Conducted calculations were verified by experimental results.

17

A low-cost embedded inertial measurement system for the monitoring of human movement

Łazoryszczak M., Peryt S.

Measurement Automation Monitoring

|

2015

|

Vol. 61, No. 12

542--544

EN

The paper presents a part of a prototype system for the monitoring of selected vital functions of humans and some preliminary results obtained from the device using implemented algorithm. The system consists of such essential modules like a microcontroller board, an inertial measurement unit and additional sensors. The main task of the device is human movement monitoring and detecting selected anomalies, e.g. fall or fainting. At the first stage, the movement classification was considered. The main movement type are walking, running and selected variants of transitions between different phases like standing up or going downstairs. The determining of the movement is based on the intuitive algorithm using raw data from accelerometers complemented by sensors like barometer and heart rate monitor. The algorithm utilizes automated multiscale-based peak detection and wavelet transform energy calculations. Finally, some further work directions and development possibilities are discussed.

18

Localization of the Wheeled Mobile Robot Based on Multi-Sensor Data Fusion

Jaroszek P., Trojnacki M.

Journal of Automation Mobile Robotics and Intelligent Systems

|

2015

|

Vol. 9, No. 3

73--84

EN

The paper presents a method of localization of a mobile robot which relies on aggregation of data from several sensors. A review of the state of the art regarding methods of localization of ground mobile robots is presented. An overview of design of the four-wheeled mobile robot used for the research is given. The way of representation of robot environment in the form of maps is described. The localization algorithm which uses the Monte Carlo localization method is described. The simulation environment and results of simulation investigations are discussed. The measurement and control equipment of the robot is described and the obtained results of experimental investigations are presented. The obtained results of simulation and experimental investigations confirm the validity of the developed robot localization method. They are the foundation of further research, where additional sensors supporting the localization process could be used.

19

A Study on the Errors in the Free-Gyro Positioning and Directional System

Jeong T.

TransNav : International Journal on Marine Navigation and Safety of Sea Transportation

|

2014

|

Vol. 8, no. 2

175--181

EN

This paper is to develop the position error equations including the attitude errors, the errors of nadir and ship’s heading, and the errors of ship’s position in the free-gyro positioning and directional system. In doing so, the determination of ship’s position by two free gyro vectors was discussed and the algorithmic design of the free-gyro positioning and directional system was introduced briefly. Next, the errors of transformation matrices of the gyro and body frames, i.e., attitude errors, were examined and the attitude equations were also derived. The perturbations of the errors of the nadir angle including ship’s heading were investigated in each stage from the sensor of rate of motion of the spin axis to the nadir angle obtained. Finally, the perturbation error equations of ship’s position used the nadir angles were derived in the form of a linear error model and the concept of FDOP was also suggested by using covariance of position error.

20

Stanowisko do badania algorytmów stosowanych w nawigacji inercyjnej

Rajchowski P.

Przegląd Telekomunikacyjny + Wiadomości Telekomunikacyjne

|

2014

|

nr 12

1448--1452

PL

Opisano budowę i działanie stanowiska do pomiarów i testowania algorytmów stosowanych w nawigacji inercyjnej. Przedstawiono opis modułów inercyjnych wraz z potencjalnymi źródłami błędów pomiarowych.

EN

The article describes a work stand for testing and developing inertial navigation algorithms. There is also a description of the inertial modules, along with potential measurement errors sources.