IEEE/AIAA Digital Avionics Systems Conference 

About: IEEE/AIAA Digital Avionics Systems Conference is an academic conference. The conference publishes majorly in the area(s): Air traffic control & Avionics. Over the lifetime, 2757 publications have been published by the conference receiving 18617 citations.

Transitioning from federated avionics architectures to Integrated Modular Avionics

Abstract: This paper identifies considerations for transitioning from a federated avionics architecture to an integrated modular avionics (IMA) architecture. Federated avionics architectures make use of distributed avionics functions that are packaged as self-contained units (LRUs and LRMs). IMA architectures employ a high-integrity, partitioned environment that hosts multiple avionics functions of different criticalities on a shared computing platform. This provides for weight and power savings since computing resources can be used more efficiently. This paper establishes the benefits of transitioning to IMA. To aid in the planning process, the paper also identifies factors to consider before transitioning to IMA. The approach to resource management (computing, communication, and I/O) is identified as the fundamental architectural difference between federated and IMA systems. The paper describes how this difference changes the development process and benefits the systems integrator. This paper also addresses misconceptions about the resource management mechanisms that can occur during a transition to IMA and concludes that resources are not inherently constrained by IMA architectures. Guidance is provided for transitioning to both "open" and "closed" IMA architectures. Open IMA architectures utilize open interface standards that are available in the public domain. Closed IMA architectures utilize proprietary interfaces that can be customized. The analysis of these avionics architectures is based upon the authors' experience in developing platform computing systems at GE Aviation. GE Aviation has developed open system IMA architectures for commercial aircraft (Boeing 787 Dreamliner), as well as military aircraft (Boeing C-130 combat aircraft, and Boeing KC-767 Tanker).

Policy compression for aircraft collision avoidance systems

Abstract: One approach to designing the decision making logic for an aircraft collision avoidance system is to frame the problem as Markov decision process and optimize the system using dynamic programming. The resulting strategy can be represented as a numeric table. This methodology has been used in the development of the ACAS X family of collision avoidance systems for manned and unmanned aircraft. However, due to the high dimensionality of the state space, discretizing the state variables can lead to very large tables. To improve storage efficiency, we propose two approaches for compressing the lookup table. The first approach exploits redundancy in the table. The table is decomposed into a set of lower-dimensional tables, some of which can be represented by single tables in areas where the lower-dimensional tables are identical or nearly identical with respect to a similarity metric. The second approach uses a deep neural network to learn a complex non-linear function approximation of the table. With the use of an asymmetric loss function and a gradient descent algorithm, the parameters for this network can be trained to provide very accurate estimates of values while preserving the relative preferences of the possible advisories for each state. As a result, the table can be approximately represented by only the parameters of the network, which reduces the required storage space by a factor of 1000. Simulation studies show that system performance is very similar using either compressed table representation in place of the original table. Even though the neural network was trained directly on the original table, the network surpasses the original table on the performance metrics and encounter sets evaluated here.

Electrical power technology for the more electric aircraft

Abstract: The Air Force's More Electric Aircraft (MEA) initiative embraces the concept of utilizing electrical power for driving aircraft subsystems currently powered by hydraulic, pneumatic or mechanical means including utility and flight control actuation, environmental control system, lubrication and fuel pumps, and numerous other utility functions. An important part of this initiative is the development and demonstration of electrical power and power electronic components and systems to enhance reliability, fault-tolerance, power density and performance. This paper describes some of the key electrical power and power electronic technologies being pursued by the Air Force to make the concept of a MEA a reality. The paper describes the results or progress to date of Air Force funded MEA programs such as the Power Management and Distribution for the More Electric Aircraft program, Integral Starter Generator program, and MOS Controlled Thyristor program. A brief discussion of future related programs is included. The integration of advanced MEA technologies is expected to increase dramatically aircraft reliability and reduce susceptibility to battle damage. The needs for aircraft maintenance and support are also expected to be reduced along with ground support equipment and maintenance personnel. >

A deep learning approach to flight delay prediction

Abstract: Deep learning has achieved significant improvement in various machine learning tasks including image recognition, speech recognition, machine translation and etc. Inspired by the huge success of the paradigm, there have been lots of tries to apply deep learning algorithms to data analytics problems with big data including traffic flow prediction. However, there has been no attempt to apply the deep learning algorithms to the analysis of air traffic data. This paper investigates the effectiveness of the deep learning models in the air traffic delay prediction tasks. By combining multiple models based on the deep learning paradigm, an accurate and robust prediction model has been built which enables an elaborate analysis of the patterns in air traffic delays. In particular, Recurrent Neural Networks (RNN) has shown its great accuracy in modeling sequential data. Day-to-day sequences of the departure and arrival flight delays of an individual airport have been modeled by the Long Short-Term Memory RNN architecture. It has been shown that the accuracy of RNN improves with deeper architectures. In this study, four different ways of building deep RNN architecture are also discussed. Finally, the accuracy of the proposed prediction model was measured, analyzed and compared with previous prediction methods. It shows best accuracy compared with all other methods.

ARINC 653 role in Integrated Modular Avionics (IMA)

Abstract: The air transport industry has developed ARINC Specification 653 as a standardized Real-Time Operating System (RTOS) interface definition. The document specifies the interface boundary between avionics software applications and the core executive software. The standardization effort was sponsored by the airline user community and involved many interested parties, including airframe manufacturers, avionics suppliers, RTOS suppliers, government and academia. ARINC 653 is a key enabler in the development of Integrated Modular Avionics (IMA). In many ways it represents a paradigm shift for avionics development; in particular it recognizes the RTOS as key component of an IMA system. The commitment shown by industry to IMA could not be more evident than that shown by the Airbus A380 and the Boeing 787 avionics suites. This paper will provide top-level overview of IMA software architecture, the key elements of the ARINC 653 standard and its current development status.