All Posts By

Elgiz Baskaya

AI in AvIAtIon

By | Chair | No Comments

We live in challenging times lately due to the pandemic; it is a fight for many sectors, and humanity. Without a doubt, aviation is one of the mostly affected industry. Those days will hopefully pass and will give way to a new rise of aviation, possibly with new tools and new applications. One of those tools is inevitably Artificial Intelligence (AI), and its applications to aviation.

The fact that AI has the potential to open doors for new possibilities in aviation has been known for a while, and a variety of organizations have already been issuing papers mentioning its potential and the expected challenges of its application [1,2,3,4].

The very nature of AI enables new functions, but also makes it difficult to be understood by us humans. The fact that it is not deterministic helps to cope with the inherently non-deterministic nature of the world, but makes it difficult to be interpreted by the humans, who are also inherently non-deterministic, yet search for determinism to predict the next outcome.  First of all, it might be useful to give a tiny bit of insight of what I mean by determinism. Well, here, I am not necessarily talking about a nice sophisticated definition of determinism, but rather the understanding of an aerospace engineer who has touched AI from one corner at one point. A deterministic system is a system, that gives the same output given the same input. Let’s say if your system is the airplane, given the same control inputs to it, you would expect it to behave in the same manner – provided of course that all the other flight conditions remain equal. Until today, all the systems used on-board an aircraft were deterministic (well, we can discuss here if a pilot behaves deterministically or not…) and the standards and certification strategies applied to it are developed to accommodate them. This gives an ease for the certification bodies to be sure how the system will behave, so that the system can be designed to achieve the expected safety requirements. But yet, just at that moment, we also sacrifice the ability to handle the unexpected situations, since we have already designed the system to deal with the expected (or in an expected range) in an expected manner. Thus, dealing with unexpected situations, might be calling for solutions of an unexpected, unpredictable nature. Then, how can we utilize AI systems, which can learn, and tackle more complicated situations but still behave safely? Do we need a new understanding of safety, do we need to look for solutions that will give answers within a safe bound even if not necessarily deterministic? How do we deal with that?

Another point is, determinism is not the only thing missing for AI solutions to be able to be covered by current certification methods; Machine Learning (ML) methods cannot be certified with current tools even if they are deterministic. As an example, if we train a classifier that will distinguish faulty phases of a flight with respect to nominal flights, and then implement it, and not change the already trained model, then the model we have is deterministic. And yet, due to some other issues such as data dependency and explainability – which we will discuss in upcoming articles – today, we cannot certify a deterministic machine learning application.

With those and similar questions in mind, Europe and US are merging their power to offer the industries the chance to enjoy the advantages of AI in aviation (not all of them necessarily new, but newly efficient). In Europe, EUROCAE WG-114 Artificial Intelligence working group aims to develop technical standards and tools to guide development and certification efforts of aeronautical systems using AI technologies. The efforts of the working group initiated with the development of a statement of concern document. Being a part of EUROCAE, the Ecole Nationale de l’Aviation Civile (ENAC) also contributes to the efforts of WG-114. Meanwhile, a parallel effort in the US by SAE, G-34 Committee for Artificial Intelligence in Aviation, decides to join the efforts of EUROCAE WG-114, thanks to the common goals shared by the two organization. Although this merge did not yet officially take place, it will enable a harmonized and enriched standardization of AI for aviation.

The standardization effort of AI for aviation systems in the course of the working group encompasses both the onboard and ground systems. The first challenge selected is to focus on the standardization of offline Neural Networks (i.e. that will not modify themselves once the aircraft is in flight), thanks to its wide expected utilization. Although it is the first phase of the effort and statement of concerns document is not yet officially published (the document is almost ready), EASA’s guideline for AI shows that the marriage between AI and Aviation is not that far [5].

AI driven flight control software is a personal interest of mine, being a person of controls in aviation. The feedback mechanism is very powerful and yet dangerous if not used properly, so giving feedback to a system by an AI driven control seems to be not the first application of AI in aviation. But yet, EASA foresees the first usable guidance for a more autonomous machine AI/ML integration to be published in 2024 and finalized in 2028 [5]. So hopefully one day…

“Our most beautiful days- we haven’t seen them yet.” Nazim Hikmet

[1] Roadmap for intelligent systems in aerospace, AIAA, Intelligent systems technical committee

[2] Artificial Intelligence with Applications for Aircraft, FAA

[3] Explainable Artificial Intelligence, XAI, DARPA

[4] Challenges in the Verification of Reinforcement Learning Algorithms – NASA

[5] Artificial Intelligence Roadmap – EASA 2020

EUROCAE Symposium and 56th General Assembly held in ENAC

By | ENAC | No Comments

EUROCAE Symposium and 56th General Assembly held in ENAC on 25-26 April 2019. With a participation of more than 200 guests, chaire drone is represented by Elgiz Baskaya as one of the moderators of the fruitful sessions of the symposium.

The main focus was on automatization both for airborne and ground systems. 

Most of the parties agreed the fact that machine learning systems will have a bigger part in the years to come but not many people are working on the certification of such adaptive systems. 

Automatization was also mentioned largely for manned aviation such as for the purpose of decreasing the required number of pilots onboard while still keeping them in the loop. Since automatization was the main topic of the event, it was almost agreed by all parties that ICAO’s definition for autonomy was not sufficient or precise anymore. So there is a need for autonomy levels for aviation as is the case for car industry.

Automatization in case of safety critical situations is discussed by European Defence Agency. They stated that they are interested in fault detection and safe ditch systems for drones, which lies parallel to the topics of interests of drone chair.

For further conclusions and highlights of the conference, please refer to link.

Thesis defense by Elgiz Baskaya on Fault diagnosis for drones

By | ENAC | No Comments

Our member Elgiz Baskaya will defend her thesis on 16/05/2019 at 10:00 am in room G11 in ENAC. We welcome you all.

Titre : ‘Fault detection and diagnosis for drones using machine learning’

Resume :

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 is to check the method’s classification ability, with a small and inexpensive chip set and without the need to access the data from the autopilot, such as the control input information.

This work addresses the faults in the control surfaces of a UAV. More specifically, the faults considered are the control surface stuck at an angle and the loss of effectiveness. First, a model of an aircraft is simulated. This model is not used for the design of Fault Detection and Diagnosis (FDD) algorithms, but is instead utilized to generate data. Simulated data are used instead of flight data in order to isolate the probable effects of the controller on the diagnosis, which may complicate a preliminary study on FDD for drones. The results show that for simulated measurements, SVM gives very accurate results on the classification of the loss of effectiveness faults on the control surfaces. These promising results call for further investigation so as to assess SVM performance on fault classification with flight data. Real flights were arranged to generate faulty flight data by manipulating the open source autopilot, Paparazzi. All data and the code are available in the code sharing and versioning system, Github. Training is held offline due to the need for labeled data and the computational burden of the tuning phase of the classifiers. Results show that from the flight data, SVM yields an F1 score of 0.98 for the classification of control surface stuck faults. For the loss of efficiency faults, some feature engineering, involving the addition of past measurements is needed in order to attain the same classification performance. A promising result is discovered when spinors are used as features instead of angular velocities. Results show that by using spinors for classification, there is a vast improvement in classification accuracy, especially when the classifiers are untuned. Using spinors and a Gaussian Kernel, an untuned classifier gives an F1 score of 0.9555, which was 0.2712 when gyro measurements were used as features. In summary, this work shows that SVM gives a satisfactory performance for the classification of faults on the control surfaces of a drone using flight data.

Jury members:

– Prof. Dr. Daniel Delahaye
– Asc. Prof. Dr. Murat Bronz
– Prof. Dr. Eric Feron
– Prof. Dr. Chingiz Hajiyev
– Asc. Prof. Philippe Truillet
– Asc. Prof. Janset Dasdemir

ENAC to host the 56th EUROCAE Symposium on the 25th and 26th April

By | ENAC | No Comments

The European Organization for Civil Aviation Equipment (EUROCAE) brings together stakeholders in the field of civil aviation with a view to establishing rules for the standardization of aeronautical systems at European and global level.

ENAC is an active member of EUROCAE, and has been supporting the European standardization activity for many years, actively participating in EUROCAE working groups and disseminating information on standards at the international level. Among the 266 EUROCAE members, from more than 37 countries, we count: manufacturers (aircraft, air and ground-based equipment, ATM systems); air service providers; national civil aviation authorities, and users (airlines, airport operators, other operators). EUROCAE works closely with the RTCA in the United States to ensure global harmonization of standards.
The conference that will take place at ENAC will cover the following areas:
– Trends for new vehicles and autonomy
– Connectivity and digital services
– Benefits and potential of ATM digital solutions
– Airport developments
– Innovations of avionics systems
– Provision of satellite services.

For information on the Symposium, please see
2019/ . Students and staff of ENAC are welcome and encouraged to participate. To participate, all you have to do is register. Online registration is free and mandatory before 17/04 at .

And the winner is :
Aircraft Upsets

By | World News | No Comments

Studies for drone regulations accelerated the pace for the assessment of risk for drone operations. A recently published ‘Annual Safety Review 2017’ discusses the aviation accidents in detail containing a chapter specialized for drones. This report by EASA, involves the data from European Central Repository (ECR) experienced by EASA member states.

With the increase in the number of drones and possibly raising consciousness on reporting occurrences, the numbers of non-fatal accidents raised by 470% in 2016 relative to 2011-2015 average, luckily maintaining zero fatalities. Most of the times, it is commercial airliner pilots to report the occurrences, and rarely the UAS pilot.

The prior key risk areas has been investigated and aircraft upsets is by far the most common cause of the occurrences and set as the first key risk to address for safe integration of drones into airspace. 50% of RPAS accidents falls in this case which often results in a damage or destruction of UAS following loss of the control of the drone by the pilot.

Second key risk area is airborne collision although it is rarely encountered due to probable frequency with exponential increase in the number of drones. Obstacle collision is the 3rd risk area which will tend to increase with integration of drones especially in urban areas.

Ref :

Along the way through integration – PART 1 : A-NPA – Introduction

By | ENAC, World News | No Comments

EASA has been assigned by European Commission to develop two main aspects:

1. EU Regulatory Framework for drone operation

2. Proposals for the regulation of low-risk drone operations, key elements of the future Implementation Rules (IRs)

With a starting point in Riga Declaration, and building up on Regulations (EC) No 216/2008 (‘Basic Regulation’), A-NPA introduces three main category of operations.

Read More