1
|
Ambrożkiewicz B, Dzienis P, Ambroziak L, Koszewnik A, Syta A, Ołdziej D, Pakrashi V. Diagnostics of unmanned aerial vehicle with recurrence based approach of piezo-element voltage signals. Sci Rep 2024; 14:17211. [PMID: 39060427 PMCID: PMC11282262 DOI: 10.1038/s41598-024-68197-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/12/2023] [Accepted: 07/22/2024] [Indexed: 07/28/2024] Open
Abstract
This work experimentally addresses damage calibration of an unmanned aerial vehicle in operational condition. A wide range of damage level and types are simulated and controlled by an electric motor via pulse width modulation in this regard. The measurement is carried out via established protocols of using a piezo-patch on one of the 8 arms, utilising the vibration sensitivity and flexibility of the arms, demonstrating repeatability of such protocol. Subsequently, recurrence analysis on the voltage time series data is performed for detection of damage. Quantifiers of damage extent are then created for the full range of damage conditions, including the extreme case of complete loss of power. Experimental baseline condition for no damage condition is also established in this regard. Both diagonal-line and vertical-line based indicators from recurrence analysis are sensitive to the quantitative estimates of damage levels and a statistical test of significance analysis confirms that it is possible to automate distinguishing the levels of damage. The damage quantifiers proposed in this paper are useful for rapid monitoring of unmanned aerial vehicle operations of connection.
Collapse
Affiliation(s)
- Bartłomiej Ambrożkiewicz
- Faculty of Mechanical Engineering, Białystok University of Technology, Wiejska 45C, 15-351, Białystok, Poland.
- Department of Technical Computer Science, Faculty of Mathematics and Technical Computer Science, Lublin University of Technology, Nadbystrzycka 38, 20-618, Lublin, Poland.
| | - Paweł Dzienis
- Faculty of Mechanical Engineering, Białystok University of Technology, Wiejska 45C, 15-351, Białystok, Poland
| | - Leszek Ambroziak
- Faculty of Mechanical Engineering, Białystok University of Technology, Wiejska 45C, 15-351, Białystok, Poland
| | - Andrzej Koszewnik
- Faculty of Mechanical Engineering, Białystok University of Technology, Wiejska 45C, 15-351, Białystok, Poland
| | - Arkadiusz Syta
- Department of Technical Computer Science, Faculty of Mathematics and Technical Computer Science, Lublin University of Technology, Nadbystrzycka 38, 20-618, Lublin, Poland
| | - Daniel Ołdziej
- Faculty of Mechanical Engineering, Białystok University of Technology, Wiejska 45C, 15-351, Białystok, Poland
| | - Vikram Pakrashi
- Centre for Mechanics, School of Mechanical and Materials Engineering, University College Dublin, Stillorgan Road, Belfield, Dublin 4, Republic of Ireland
| |
Collapse
|
2
|
Marrero D, Kern J, Urrea C. A Novel Robotic Controller Using Neural Engineering Framework-Based Spiking Neural Networks. SENSORS (BASEL, SWITZERLAND) 2024; 24:491. [PMID: 38257584 PMCID: PMC10819625 DOI: 10.3390/s24020491] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 12/26/2023] [Revised: 01/11/2024] [Accepted: 01/11/2024] [Indexed: 01/24/2024]
Abstract
This paper investigates spiking neural networks (SNN) for novel robotic controllers with the aim of improving accuracy in trajectory tracking. By emulating the operation of the human brain through the incorporation of temporal coding mechanisms, SNN offer greater adaptability and efficiency in information processing, providing significant advantages in the representation of temporal information in robotic arm control compared to conventional neural networks. Exploring specific implementations of SNN in robot control, this study analyzes neuron models and learning mechanisms inherent to SNN. Based on the principles of the Neural Engineering Framework (NEF), a novel spiking PID controller is designed and simulated for a 3-DoF robotic arm using Nengo and MATLAB R2022b. The controller demonstrated good accuracy and efficiency in following designated trajectories, showing minimal deviations, overshoots, or oscillations. A thorough quantitative assessment, utilizing performance metrics like root mean square error (RMSE) and the integral of the absolute value of the time-weighted error (ITAE), provides additional validation for the efficacy of the SNN-based controller. Competitive performance was observed, surpassing a fuzzy controller by 5% in terms of the ITAE index and a conventional PID controller by 6% in the ITAE index and 30% in RMSE performance. This work highlights the utility of NEF and SNN in developing effective robotic controllers, laying the groundwork for future research focused on SNN adaptability in dynamic environments and advanced robotic applications.
Collapse
Affiliation(s)
| | - John Kern
- Electrical Engineering Department, Faculty of Engineering, University of Santiago of Chile (USACH), Av. Víctor Jara 3519, Estación Central, Santiago 9170124, Chile; (D.M.); (C.U.)
| | | |
Collapse
|
3
|
Karakostas C, Quaranta G, Chatzi E, Zülfikar AC, Çetindemir O, De Roeck G, Döhler M, Limongelli MP, Lombaert G, Apaydın NM, Pakrashi V, Papadimitriou C, Yeşilyurt A. Seismic assessment of bridges through structural health monitoring: a state-of-the-art review. BULLETIN OF EARTHQUAKE ENGINEERING 2023; 22:1309-1357. [PMID: 38419620 PMCID: PMC10896794 DOI: 10.1007/s10518-023-01819-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 03/25/2023] [Accepted: 10/31/2023] [Indexed: 03/02/2024]
Abstract
The present work offers a comprehensive overview of methods related to condition assessment of bridges through Structural Health Monitoring (SHM) procedures, with a particular interest on aspects of seismic assessment. Established techniques pertaining to different levels of the SHM hierarchy, reflecting increasing detail and complexity, are first outlined. A significant portion of this review work is then devoted to the overview of computational intelligence schemes across various aspects of bridge condition assessment, including sensor placement and health tracking. The paper concludes with illustrative examples of two long-span suspension bridges, in which several instrumentation aspects and assessments of seismic response issues are discussed.
Collapse
Affiliation(s)
- Christos Karakostas
- Institute of Engineering Seismology and Earthquake Engineering, Research Unit of Earthquake Planning and Protection Organization, Thessaloniki, Greece
| | - Giuseppe Quaranta
- Department of Structural and Geotechnical Engineering, Sapienza University of Rome, Rome, Italy
| | - Eleni Chatzi
- Department of Civil, Environmental and Geomatic Engineering, ETH Zürich, Zurich, Switzerland
| | | | - Oğuzhan Çetindemir
- Department of Civil Engineering, Gebze Technical University, Kocaeli, Türkiye
| | - Guido De Roeck
- Department of Civil Engineering, Katholieke Universiteit Leuven, Leuven, Belgium
| | - Michael Döhler
- Université Gustave Eiffel, Inria, COSYS-SII, I4S, Rennes, France
| | - Maria Pina Limongelli
- Department of Architecture, Built Environment and Construction Engineering, Politecnico di Milano, Milan, Italy
| | - Geert Lombaert
- Department of Civil Engineering, Katholieke Universiteit Leuven, Leuven, Belgium
| | | | - Vikram Pakrashi
- UCD Centre for Mechanics, Dynamical Systems and Risk Laboratory, School of Mechanical and Materials Engineering, University College Dublin, Dublin, Ireland
| | | | - Ali Yeşilyurt
- Disaster Management Institute, Istanbul Technical University, Istanbul, Türkiye
| |
Collapse
|