AIAA SPACE 2012 Conference & Exposition, Sep 11, 2012
This paper focuses on the design issues of ITUpSAT II which is the second nanosatellite project o... more This paper focuses on the design issues of ITUpSAT II which is the second nanosatellite project of the Controls and Avionics Laboratory of ITU. The idea ITUpSAT II is to develop a standardized but reconfigurable bus architecture which can serve as a standard platform for a variety of space science missions. The configuration is compliant with 3U CubeSat Standards as to enable simple access to space. In addition, the design mainly utilizes in-house space-modified COTS components as to reduce the manufacturing costs. In comparison to the existing on-market pico/nano-satellite buses, ITUpSAT II bus provides not only higher computational power and data link capabilities but also precise orbit determination through its GPS receiver. To cope up with different requirements across a wide range of scientific missions, an indigenous ADCS for precise attitude control is developed. Embedded within the ADCS is a suite of attitude determination and controller algorithms with different operation modes as to fulfill the pointing accuracy needs depending on the mission. Furthermore, the modular subsystem structure enables ADCS and S-Band data link to serve as a standalone payload computer.
This article presents a new machine learning (ML) development lifecycle which will constitute the... more This article presents a new machine learning (ML) development lifecycle which will constitute the core of the new aeronautical standard on ML called AS6983, jointly being developed by working group WG-114/G34 of EUROCAE and SAE. The article also presents a survey of several existing standards and guidelines related to ML in aeronautics, automotive, and industrial domains by comparing and contrasting their scope, purpose, and results. Standards and guidelines reviewed include the European Union Aviation Safety Agency (EASA) Concept Paper, the DEEL (DEpendable and Explainable Learning) white paper “Machine Learning in Certified Systems”, Aerospace Vehicle System Institute (AVSI) Authorization for Expenditure (AFE) 87 report on Machine Learning, Guidance on the Assurance of Machine Learning for use in Autonomous Systems (AMLAS), Laboratoire National de Metrologie et d’Essais (LNE) Certification Standard of Processes for AI, the Underwriters Laboratories (UL) 4600 Safety Standard for Au...
The number of Unmanned Aerial System (UAS) applications is quickly increasing as technology, stan... more The number of Unmanned Aerial System (UAS) applications is quickly increasing as technology, standards and regulation allow them. With each new application, more industrial sectors get affected, and the retail sector is already being impacted. This paper presents five UAS applications that will impact the retail sector: freight, monitoring, guiding, delivery, and advertisement. For each application, concepts of operation are provided along with the associated technological, standard and regulatory locks. These operations are then organized along time, from earliest to latest accessible, with accompanying explanation as to why and when. It is shown that the applications currently most publicized are not the ones that will come first. Finally, a discussion regarding the accuracy of our forecast is proposed and leads to support the enabling of drones, in the retail sector, are provided.
Loss of control is a severe and immediate consequence of faults in an unmanned aircraft system du... more Loss of control is a severe and immediate consequence of faults in an unmanned aircraft system during flight. Without recovery, detection of admissible landing spots is necessary to avoid causalities. This case study considers exemplary the MAKO unmanned aircraft and discusses viable trim conditions for a drone system after faults of propulsion and elevator using continuation analysis. Furthermore, simple estimates of reachable zones for controlled flight into terrain are provided.
Cette nouvelle ere de petits UAV qui peuplent actuellement l'espace aerien souleve de nombreu... more Cette nouvelle ere de petits UAV qui peuplent actuellement l'espace aerien souleve de nombreuses preoccupations en matiere de securite, en raison de l'absence de pilote a bord et de la nature moins precise des capteurs. Cela necessite des approches intelligentes pour faire face aux situations d'urgence qui se produiront inevitablement pour toutes les categories d'operations d'UAV telles que definies par l'AESA (Agence europeenne de la securite aerienne). Les limitations materielles de ces petits vehicules suggerent l'utilisation de la redondance analytique plutot que la pratique habituelle de la redondance materielle dans l'aviation humaine. Au cours de cette etude, des pratiques d'apprentissage automatique sont mises en œuvre afin de diagnostiquer les defaillances d'un petit drone a voilure fixe afin d'eviter le fardeau de la modelisation precise necessaire au diagnostic par le modele. Une methode de classification supervisee, SVM (Suppor...
This new era of small UAVs currently populating the airspace introduces many safety concerns, due... more This new era of small UAVs currently populating the airspace introduces many safety concerns, due to the absence of a pilot onboard and the less accurate nature of the sensors. This necessitates intelligent approaches to address the emergency situations that will inevitably arise for all classes of UAV operations as defined by EASA (European Aviation Safety Agency). Hardware limitations for these small vehicles point to the utilization of analytical redundancy, rather than to the usual practice of hardware redundancy in manned aviation. In the course of this study, machine learning practices are implemented in order to diagnose faults on a small fixed-wing UAV to avoid the burden of accurate modeling needed in model-based fault diagnosis. A supervised classification method, SVM (Support Vector Machines) is used to classify the faults. The data used to diagnose the faults are gyro and accelerometer measurements. The idea to restrict the data set to accelerometer and gyro measurements...
In this work, the application of Generalized Differential Quadrature Method (GDQM) to solve a var... more In this work, the application of Generalized Differential Quadrature Method (GDQM) to solve a variable viscosity channel flow under constant magnetic field is investigated. The governing equations for channel flow in between two infinite horizontal parallel porous plates subject to convective surface boundary conditions are given in dimensional and non-dimensional forms, pointing out the dimensionless parameters used. These equations are discretized using the GDQM, and solved via Newton Raphson Method. Effects of magnetic field on incompressible electrically conducting fluid velocity and temperature profiles are presented in plots.
This paper focuses on the design issues of ITUpSAT II which is the second nanosatellite project o... more This paper focuses on the design issues of ITUpSAT II which is the second nanosatellite project of the Controls and Avionics Laboratory of ITU. The idea ITUpSAT II is to develop a standardized but reconfigurable bus architecture which can serve as a standard platform for a variety of space science missions. The configuration is compliant with 3U CubeSat Standards as to enable simple access to space. In addition, the design mainly utilizes in-house space-modified COTS components as to reduce the manufacturing costs. In comparison to the existing on-market pico/nano-satellite buses, ITUpSAT II bus provides not only higher computational power and data link capabilities but also precise orbit determination through its GPS receiver. To cope up with different requirements across a wide range of scientific missions, an indigenous ADCS for precise attitude control is developed. Embedded within the ADCS is a suite of attitude determination and controller algorithms with different operation modes as to fulfill the pointing accuracy needs depending on the mission. Furthermore, the modular subsystem structure enables ADCS and S-Band data link to serve as a standalone payload computer.
Gökcisimleri arasindaki gravitasyonel etkilesmeleri formüle eden nonlineer denklemlerin yapisi, b... more Gökcisimleri arasindaki gravitasyonel etkilesmeleri formüle eden nonlineer denklemlerin yapisi, bunlarin bilgisayar yardimi olmaksizin integre edilmesine genellikle imkan vermemektedir. Gelenekselolarak, Günes Sistemi'ne ait gezegen, uydu, kuyruklu yildiz ve asteroid gibi gökcisimlerinin hareketlerinin incelenmesi, bunlari birbirinden yalitilmis birer iki-cisim problemine indirgeyerek ele almaya dayanir Bilindigi gibi, bu problemlerin çözümleri, "konik kesitleri" olan fonksiyonlar seklinde bulunmakta ve gerektiginde ikiden fazla sayidaki cismin hareketi de, iki-cisim problemi üzerine eklenen bazi pertürbasyonlar yardimiyla belirlenebilmektedir. Gezegenlerin, ikicisimproblemi modeline göre, Günes çevresindeki· yaklasik dairesel yörüngeler üzerinde hareket ettigi sonucu gözlemlerle de uyusmaktadir. Buna karsilik, kuyruklu yildiz yörüngelerinin parametrelerinde zamanla, öngörülemeyen degisikliklerin ortaya çikabildigi gözlenmektedir. Diger taraftan, Astrodinamigin uzayara...
2017 IEEE/AIAA 36th Digital Avionics Systems Conference (DASC), 2017
The new era of small UAVs necessitates intelligent approaches towards the issue of fault diagnosi... more The new era of small UAVs necessitates intelligent approaches towards the issue of fault diagnosis to ensure a safe flight. A recent attempt to accommodate quite a number of UAVs in the airspace requires to assure a safety level. The hardware limitations for these small vehicles point the utilization of analytical redundancy rather than the usual practice of hardware redundancy in the conventional flights. In the course of this study, fault detection and diagnosis for aircraft is reviewed. An approach of implementing machine learning practices to diagnose faults on a small fixed-wing is selected. The selection criteria behind is that, data-driven fault diagnosis enables avoiding the burden of accurate modeling needed in model-based fault diagnosis. In this study, first, a model of an aircraft is simulated. This model is not used for the design of Fault Detection and Diagnosis (FDD) algorithms, but instead utilized to generate data and test the designed algorithms. The measurements are simulated using the statistics of the hardware in the house. Simulated data is opted instead of flight data to isolate the probable effects of the controller on the diagnosis, which will complicate this preliminary study on FDD for drones. A supervised classification method, SVM (Support Vector Machines) is used to classify the faulty and nominal flight conditions. The features selected are the gyro and accelerometer measurements. The fault considered is loss of effectiveness in the control surfaces of the drone. Principle component analysis is used to investigate the data by reducing the feature space dimension. The training is held offline due to the need of labeled data. The results show that for simulated measurements, SVM gives very accurate results on the classification of loss of effectiveness fault on the control surfaces.
2020 AIAA/IEEE 39th Digital Avionics Systems Conference (DASC), 2020
Machine learning is among the top research topics of the last decade in terms of practicality and... more Machine learning is among the top research topics of the last decade in terms of practicality and popularity. Though often unnoticed, machine learning guides many aspects of our lives since its introduction via the big tech companies. Its abilities rise, defeating 9-dan Go professional, their accuracy increase, enabling smooth voice recognition, adding intelligence to our daily lives. However, its development is mostly supported by high tech companies for now rather than the public, or regulations, who show increasing concern about its usage. Despite some reluctance, machine learning has started to appear in aviation as well. Operational improvements were among the first applications. In this paper, we offer to present an introduction to machine learning, compare it with well known modeling techniques by giving an example from aviation and question their fitness for certification. We discuss the enablers and try to understand the limitations that might result or prevent the use of machine learning on certified safety systems. Similar considerations are held for systems that do not require certification, but need to be taken into account in risk analysis methods. The ultimate purpose of this paper is to highlight the existing challenges which prevent machine learning algorithms from having a wider role in drone avionics, and more generally in aviation.
Last decade witnessed the rapid increase in number of drones of various purposes. This pushes the... more Last decade witnessed the rapid increase in number of drones of various purposes. This pushes the regulators to rush for safe integration strategies in a way to properly share the utilization of airspace. Accommodating faults and failures is one of the key issues since they constitute the bigger chunk in the occurrence reports available. The hardware limitations for these small vehicles point the utilization of analytical redundancy rather than the usual practice of hardware redundancy in the conventional flights. In the course of this study, fault detection and diagnosis for aircraft is reviewed. Then a nonlinear model for MAKO aircraft is simulated to generate faulty and nominal flight data. This platform enables to generate data for various flight conditions and design machine learning implementations for fault detection and diagnosis.
AIAA SPACE 2012 Conference & Exposition, Sep 11, 2012
This paper focuses on the design issues of ITUpSAT II which is the second nanosatellite project o... more This paper focuses on the design issues of ITUpSAT II which is the second nanosatellite project of the Controls and Avionics Laboratory of ITU. The idea ITUpSAT II is to develop a standardized but reconfigurable bus architecture which can serve as a standard platform for a variety of space science missions. The configuration is compliant with 3U CubeSat Standards as to enable simple access to space. In addition, the design mainly utilizes in-house space-modified COTS components as to reduce the manufacturing costs. In comparison to the existing on-market pico/nano-satellite buses, ITUpSAT II bus provides not only higher computational power and data link capabilities but also precise orbit determination through its GPS receiver. To cope up with different requirements across a wide range of scientific missions, an indigenous ADCS for precise attitude control is developed. Embedded within the ADCS is a suite of attitude determination and controller algorithms with different operation modes as to fulfill the pointing accuracy needs depending on the mission. Furthermore, the modular subsystem structure enables ADCS and S-Band data link to serve as a standalone payload computer.
This article presents a new machine learning (ML) development lifecycle which will constitute the... more This article presents a new machine learning (ML) development lifecycle which will constitute the core of the new aeronautical standard on ML called AS6983, jointly being developed by working group WG-114/G34 of EUROCAE and SAE. The article also presents a survey of several existing standards and guidelines related to ML in aeronautics, automotive, and industrial domains by comparing and contrasting their scope, purpose, and results. Standards and guidelines reviewed include the European Union Aviation Safety Agency (EASA) Concept Paper, the DEEL (DEpendable and Explainable Learning) white paper “Machine Learning in Certified Systems”, Aerospace Vehicle System Institute (AVSI) Authorization for Expenditure (AFE) 87 report on Machine Learning, Guidance on the Assurance of Machine Learning for use in Autonomous Systems (AMLAS), Laboratoire National de Metrologie et d’Essais (LNE) Certification Standard of Processes for AI, the Underwriters Laboratories (UL) 4600 Safety Standard for Au...
The number of Unmanned Aerial System (UAS) applications is quickly increasing as technology, stan... more The number of Unmanned Aerial System (UAS) applications is quickly increasing as technology, standards and regulation allow them. With each new application, more industrial sectors get affected, and the retail sector is already being impacted. This paper presents five UAS applications that will impact the retail sector: freight, monitoring, guiding, delivery, and advertisement. For each application, concepts of operation are provided along with the associated technological, standard and regulatory locks. These operations are then organized along time, from earliest to latest accessible, with accompanying explanation as to why and when. It is shown that the applications currently most publicized are not the ones that will come first. Finally, a discussion regarding the accuracy of our forecast is proposed and leads to support the enabling of drones, in the retail sector, are provided.
Loss of control is a severe and immediate consequence of faults in an unmanned aircraft system du... more Loss of control is a severe and immediate consequence of faults in an unmanned aircraft system during flight. Without recovery, detection of admissible landing spots is necessary to avoid causalities. This case study considers exemplary the MAKO unmanned aircraft and discusses viable trim conditions for a drone system after faults of propulsion and elevator using continuation analysis. Furthermore, simple estimates of reachable zones for controlled flight into terrain are provided.
Cette nouvelle ere de petits UAV qui peuplent actuellement l'espace aerien souleve de nombreu... more Cette nouvelle ere de petits UAV qui peuplent actuellement l'espace aerien souleve de nombreuses preoccupations en matiere de securite, en raison de l'absence de pilote a bord et de la nature moins precise des capteurs. Cela necessite des approches intelligentes pour faire face aux situations d'urgence qui se produiront inevitablement pour toutes les categories d'operations d'UAV telles que definies par l'AESA (Agence europeenne de la securite aerienne). Les limitations materielles de ces petits vehicules suggerent l'utilisation de la redondance analytique plutot que la pratique habituelle de la redondance materielle dans l'aviation humaine. Au cours de cette etude, des pratiques d'apprentissage automatique sont mises en œuvre afin de diagnostiquer les defaillances d'un petit drone a voilure fixe afin d'eviter le fardeau de la modelisation precise necessaire au diagnostic par le modele. Une methode de classification supervisee, SVM (Suppor...
This new era of small UAVs currently populating the airspace introduces many safety concerns, due... more This new era of small UAVs currently populating the airspace introduces many safety concerns, due to the absence of a pilot onboard and the less accurate nature of the sensors. This necessitates intelligent approaches to address the emergency situations that will inevitably arise for all classes of UAV operations as defined by EASA (European Aviation Safety Agency). Hardware limitations for these small vehicles point to the utilization of analytical redundancy, rather than to the usual practice of hardware redundancy in manned aviation. In the course of this study, machine learning practices are implemented in order to diagnose faults on a small fixed-wing UAV to avoid the burden of accurate modeling needed in model-based fault diagnosis. A supervised classification method, SVM (Support Vector Machines) is used to classify the faults. The data used to diagnose the faults are gyro and accelerometer measurements. The idea to restrict the data set to accelerometer and gyro measurements...
In this work, the application of Generalized Differential Quadrature Method (GDQM) to solve a var... more In this work, the application of Generalized Differential Quadrature Method (GDQM) to solve a variable viscosity channel flow under constant magnetic field is investigated. The governing equations for channel flow in between two infinite horizontal parallel porous plates subject to convective surface boundary conditions are given in dimensional and non-dimensional forms, pointing out the dimensionless parameters used. These equations are discretized using the GDQM, and solved via Newton Raphson Method. Effects of magnetic field on incompressible electrically conducting fluid velocity and temperature profiles are presented in plots.
This paper focuses on the design issues of ITUpSAT II which is the second nanosatellite project o... more This paper focuses on the design issues of ITUpSAT II which is the second nanosatellite project of the Controls and Avionics Laboratory of ITU. The idea ITUpSAT II is to develop a standardized but reconfigurable bus architecture which can serve as a standard platform for a variety of space science missions. The configuration is compliant with 3U CubeSat Standards as to enable simple access to space. In addition, the design mainly utilizes in-house space-modified COTS components as to reduce the manufacturing costs. In comparison to the existing on-market pico/nano-satellite buses, ITUpSAT II bus provides not only higher computational power and data link capabilities but also precise orbit determination through its GPS receiver. To cope up with different requirements across a wide range of scientific missions, an indigenous ADCS for precise attitude control is developed. Embedded within the ADCS is a suite of attitude determination and controller algorithms with different operation modes as to fulfill the pointing accuracy needs depending on the mission. Furthermore, the modular subsystem structure enables ADCS and S-Band data link to serve as a standalone payload computer.
Gökcisimleri arasindaki gravitasyonel etkilesmeleri formüle eden nonlineer denklemlerin yapisi, b... more Gökcisimleri arasindaki gravitasyonel etkilesmeleri formüle eden nonlineer denklemlerin yapisi, bunlarin bilgisayar yardimi olmaksizin integre edilmesine genellikle imkan vermemektedir. Gelenekselolarak, Günes Sistemi'ne ait gezegen, uydu, kuyruklu yildiz ve asteroid gibi gökcisimlerinin hareketlerinin incelenmesi, bunlari birbirinden yalitilmis birer iki-cisim problemine indirgeyerek ele almaya dayanir Bilindigi gibi, bu problemlerin çözümleri, "konik kesitleri" olan fonksiyonlar seklinde bulunmakta ve gerektiginde ikiden fazla sayidaki cismin hareketi de, iki-cisim problemi üzerine eklenen bazi pertürbasyonlar yardimiyla belirlenebilmektedir. Gezegenlerin, ikicisimproblemi modeline göre, Günes çevresindeki· yaklasik dairesel yörüngeler üzerinde hareket ettigi sonucu gözlemlerle de uyusmaktadir. Buna karsilik, kuyruklu yildiz yörüngelerinin parametrelerinde zamanla, öngörülemeyen degisikliklerin ortaya çikabildigi gözlenmektedir. Diger taraftan, Astrodinamigin uzayara...
2017 IEEE/AIAA 36th Digital Avionics Systems Conference (DASC), 2017
The new era of small UAVs necessitates intelligent approaches towards the issue of fault diagnosi... more The new era of small UAVs necessitates intelligent approaches towards the issue of fault diagnosis to ensure a safe flight. A recent attempt to accommodate quite a number of UAVs in the airspace requires to assure a safety level. The hardware limitations for these small vehicles point the utilization of analytical redundancy rather than the usual practice of hardware redundancy in the conventional flights. In the course of this study, fault detection and diagnosis for aircraft is reviewed. An approach of implementing machine learning practices to diagnose faults on a small fixed-wing is selected. The selection criteria behind is that, data-driven fault diagnosis enables avoiding the burden of accurate modeling needed in model-based fault diagnosis. In this study, first, a model of an aircraft is simulated. This model is not used for the design of Fault Detection and Diagnosis (FDD) algorithms, but instead utilized to generate data and test the designed algorithms. The measurements are simulated using the statistics of the hardware in the house. Simulated data is opted instead of flight data to isolate the probable effects of the controller on the diagnosis, which will complicate this preliminary study on FDD for drones. A supervised classification method, SVM (Support Vector Machines) is used to classify the faulty and nominal flight conditions. The features selected are the gyro and accelerometer measurements. The fault considered is loss of effectiveness in the control surfaces of the drone. Principle component analysis is used to investigate the data by reducing the feature space dimension. The training is held offline due to the need of labeled data. The results show that for simulated measurements, SVM gives very accurate results on the classification of loss of effectiveness fault on the control surfaces.
2020 AIAA/IEEE 39th Digital Avionics Systems Conference (DASC), 2020
Machine learning is among the top research topics of the last decade in terms of practicality and... more Machine learning is among the top research topics of the last decade in terms of practicality and popularity. Though often unnoticed, machine learning guides many aspects of our lives since its introduction via the big tech companies. Its abilities rise, defeating 9-dan Go professional, their accuracy increase, enabling smooth voice recognition, adding intelligence to our daily lives. However, its development is mostly supported by high tech companies for now rather than the public, or regulations, who show increasing concern about its usage. Despite some reluctance, machine learning has started to appear in aviation as well. Operational improvements were among the first applications. In this paper, we offer to present an introduction to machine learning, compare it with well known modeling techniques by giving an example from aviation and question their fitness for certification. We discuss the enablers and try to understand the limitations that might result or prevent the use of machine learning on certified safety systems. Similar considerations are held for systems that do not require certification, but need to be taken into account in risk analysis methods. The ultimate purpose of this paper is to highlight the existing challenges which prevent machine learning algorithms from having a wider role in drone avionics, and more generally in aviation.
Last decade witnessed the rapid increase in number of drones of various purposes. This pushes the... more Last decade witnessed the rapid increase in number of drones of various purposes. This pushes the regulators to rush for safe integration strategies in a way to properly share the utilization of airspace. Accommodating faults and failures is one of the key issues since they constitute the bigger chunk in the occurrence reports available. The hardware limitations for these small vehicles point the utilization of analytical redundancy rather than the usual practice of hardware redundancy in the conventional flights. In the course of this study, fault detection and diagnosis for aircraft is reviewed. Then a nonlinear model for MAKO aircraft is simulated to generate faulty and nominal flight data. This platform enables to generate data for various flight conditions and design machine learning implementations for fault detection and diagnosis.
Uploads