No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Predictive Maintenance and Performance Optimisation in Aircrafts using Data Analytics
Abstract and Figures
Airline industry has provided a significantly
conventional, faster and reliable mode of transportation for
passengers and freight over the decades in which the industry
has been in service despite the pressure being applied especially
in maintaining operational affordability. The study critically
reviews the techniques and tools, infrastructure and general
application architecture for discussing the applicability of data
analytics based on both batch processing and real time stream
data in general aviation for health monitoring and predictive
analysis in order to predict maintenance and optimize the
performance of aircrafts. In this respect, the study further
evaluates the significant capability in addressing contemporary
problems which are uniquely addressed by data analytics
system.
Figures - uploaded by Shakthi Weerasinghe
Author content
All figure content in this area was uploaded by Shakthi Weerasinghe
Content may be subject to copyright.
... Due to the increasing use of various technologies in aircraft and the modernizing of maintenance planning, future aviation maintenance technicians will work in a highly technological environment. This includes implementing predictive maintenance technologies and practices in order to decrease schedule interruptions such as delays and cancellations and unscheduled maintenance (Vianna & Yoneyama, 2018;Weerasinghe & Ahangama, 2018). Boeing's Airplane Health Monitoring (AHM) program is one example and uses continuous monitoring and analysis of aircraft systems performance and condition data to enable organizations to make decisions about what maintenance should be performed and when (Boeing, 2009). ...
The requirements of analyzing heterogeneous data streams and detecting complex patterns in near real-time have raised the prospect of Complex Event Processing (CEP) for many internet of things (IoT) applications. Although CEP provides a scalable and distributed solution for analyzing complex data streams on the fly, it is designed for reactive applications as CEP acts on near real-time data and does not exploit historical data. In this regard, we propose a proactive architecture which exploits historical data using machine learning (ML) for prediction in conjunction with CEP. We propose an adaptive prediction algorithm called Adaptive Moving Window Regression (AMWR) for dynamic IoT data and evaluated it using a real-world use case with an accuracy of over 96%. It can perform accurate predictions in near real-time due to reduced complexity and can work along CEP in our architecture. We implemented our proposed architecture using open source components which are optimized for big data applications and validated it on a use-case from Intelligent Transportation Systems (ITS). Our proposed architecture is reliable and can be used across different fields in order to predict complex events.
This paper describes a series of short experiments collecting and analyzing ADS B data using IoT (Internet of Things) devices. The collection is performed using a Raspberry Pi single board computer, an RTL-SDR radio, custom software written for the project, and the open source dump1090 software program. This Raspberry Pi/RTL-SDR/dump1090 combination is used to collect ADS-B data. The data is captured and archived using a software program that reads the ADS-B data in real time as it is received by the RTL-SDR radio and subsequently output by the dump1090 program. The captured data is written to a series of flat files. Subsequent analytics and analysis is performed using the R programming language and the R Studio environment. The paper describes a subset of the R code that that was used in the analysis. All of the custom software used in this project is freely available at GitHub (see References section).
Airline industry is characterized by large quantities of complex, unstructured and rapid changing data that can be categorized as big data, requiring specialized analysis tools to explore it with the purpose of obtaining useful knowledge as decision support for companies that need to fundament their activities and improve the processes they are carrying on. In this context, business
intelligence tools are valuable instruments that can optimally process airline related data so that the activities that are conducted can be optimized to maximize profits, while meeting customer requirements. An airline company that has access to large volumes of data (stored into conventional or big data repositories) has two options to extract useful decision support information: processing data by using general-purpose business intelligence systems or processing data by using industry
specific business intelligence systems. Each of these two options has both advantages and disadvantages for the airline companies that intend to use them. The present paper presents a
comparative study of a number of general-purpose and airline industry specific business intelligence systems, together with their main advantages and disadvantages.
In this paper we present an innovative monitoring system, namely TLSensing, that can be integrated in future aerial vehicles for supporting the development of advanced health management systems. Based on the revolutionary Internet of Things paradigm and emerging open standards for low-power and short-range wireless technologies, it intends to enable pervasive monitoring services through the diffusion of a large number of sensors around the aircraft, which continuously capture critical and non critical parameters from on-board equipments and the environment and deliver them to the remote monitoring devices through wireless communication links. In summary, TLSensing is composed by a number of constrained devices equipped with sensing and wireless communication capabilities, a central system coordinator that controls data acquisition processes through a dedicated monitoring software, and a web server application that collects data coming from the network and makes them available to the user and to external software entities belonging to the health management system. Starting from the description of the technological background that motivated the development of the presented platform, we will carefully describe both hardware and software components integrated in TLSensing, alongside their interaction and the most important features they cover. Moreover, to provide a further insight, we will also present how TLSensing works by showing some measurements collected with an experimental testbed deployed in our research laboratory.
The goal of this work is to build an aircraft fault diagnosis and decision system, which uses data-driven methods to automatically detect and isolate faults in the aircraft, while keeping its reliability and safety. As a fundamental specification, this fault diagnosis system should not be a black box, the condition monitoring and the results of comprehensive diagnosis shall be illuminated to engineering consulting services, and it can help engineers to accumulate the knowledge for reengineering purposes (including diagnosis operational rules) and improve the design of new aircraft. In comparison with some methods, Artificial Neural Networks (ANN) has been shown to be more advantageous and is currently used in fault diagnosis system. For example, it hasn't any problem of conflict of new rules, which is a big problem in Expert System while adding new fault. In this work, ANN is improved. Its speed of learning and the iteration times can be self-corrected or mutated. Moreover, neural network can be combined with other optimization methods, like genetic methods, to achieve a better performance. Furthermore, according to the different types of sensors, certain sub-networks are built to assist the principal network or replace it in some anomaly condition. A decision system treats the results of all the networks and comes to a conclusion, which will be sent to pilot, airport command center (ACC), or fault tolerant system.
We study dynamic reliability of systems where system components age with a constant failure rate and there is a budget constraint. We develop a methodology to effectively prepare a predictive maintenance plan of such a system using dynamic Bayesian networks (DBNs). DBN representation allows monitoring the system reliability in a given planning horizon and predicting the system state under different replacement plans. When the system reliability falls below a predetermined threshold value, component replacements are planned such that maintenance budget is not exceeded. The decision of which component(s) to replace is an important issue since it affects future system reliability and consequently the next time to do replacement. Component marginal probabilities given the system state are used to determine which component(s) to replace. Two approaches are proposed in calculating the marginal probabilities of components. The first is a myopic approach where the only evidence belongs to the current planning time. The second is a look-ahead approach where all the subsequent time intervals are included as evidence.
This article provides an overview of the development and standardizations of connectivity solutions for enabling the Industrial Internet of Things (IIoT). It also highlights key IIoT connectivity technologies and platforms that have the potential of driving the next industrial revolution. In addition, the article addresses the main challenges standing in the way of realizing the full potential of the IIoT, namely attaining secure connectivity and managing a vastly fragmented ecosystem of connectivity solutions and platforms. Finally, IIoT connectivity challenges are illustrated by the example of future building automation.
Integrated vehicle health management (IVHM) technology focused on the aircraft-level fault diagnosis, prediction and health management. The application of IVHM is the inevitable development trend of the next generation aircraft CBM, it is important for aircraft to improve security, maintainability, performance and reduce the operation cost. This paper based on a large number of documents, describes the meanings and the development process of IVHMS, analyzes the difficulties and the key technologies of IVHM research. At the end of the paper, the technical development prospect was discussed. The author hopes that readers have a more detailed understanding of IVHM state-of-art and the future direction.
Nowadays, aviation is getting more necessary for our daily life. Airplane is becoming an important method of passenger transport and cargo transport. Integrated health management of airplanes strongly influences the maintenance efficiency of civil fleets and military fleets as wells as drone fleets. This paper proposes a framework of airplane integrated health management that provides integrated health management of airplanes running in worldwide and monitors health status of flight in order to build a suitable mechanism for managing the real-time fault diagnostics, fault prediction, as well as intelligent maintenance decision of airplanes.
Aircraft emissions are a significant source of pollution and are closely related to engine fuel burn. The onboard Flight Data Recorder (FDR) is an accurate source of information as it logs operational aircraft data in situ. The main objective of this paper is the visualization and exploration of data from the FDR. The Airbus A330 - 223 is used to study the variation of normalized engine performance parameters with the altitude profile in all the phases of flight. A turbofan performance analysis model is employed to calculate the theoretical thrust and it is shown to be a good qualitative match to the FDR reported thrust. The operational thrust settings and the times in mode are found to differ significantly from the ICAO standard values in the LTO cycle. This difference can lead to errors in the calculation of aircraft emission inventories. This paper is the first step towards the accurate estimation of engine performance and emissions for different aircraft and engine types, given the trajectory of an aircraft.
This paper identifies key aviation data sets for operational analytics, presents a methodology for application of big-data analysis methods to operational problems, and offers examples of analytical solutions using an integrated aviation data warehouse. Big-data analysis methods have revolutionized how both government and commercial researchers can analyze massive aviation databases that were previously too cumbersome, inconsistent or irregular to drive high-quality output. Traditional data-mining methods are effective on uniform data sets such as flight tracking data or weather. Integrating heterogeneous data sets introduces complexity in data standardization, normalization, and scalability. The variability of underlying data warehouse can be leveraged using virtualized cloud infrastructure for scalability to identify trends and create actionable information. The applications for big-data analysis in airspace system performance and safety optimization have high potential because of the availability and diversity of airspace related data. Analytical applications to quantitatively review airspace performance, operational efficiency and aviation safety require a broad data set. Individual information sets such as radar tracking data or weather reports provide slices of relevant data, but do not provide the required context, perspective and detail on their own to create actionable knowledge. These data sets are published by diverse sources and do not have the standardization, uniformity or defect controls required for simple integration and analysis. At a minimum, aviation big-data research requires the fusion of airline, aircraft, flight, radar, crew, and weather data in a uniform taxonomy, organized so that queries can be automated by flight, by fleet, or across the airspace system.
Nowadays, as fuel is an important resource for the whole world, researchers are trying a variety machine learning models for fuel flow prediction in industry, aerospace specifically. Different machine learning models have been applied in different applications. This paper will analyze these applications. Many useful points have been found by comparison of those experimental results.
FDA provide a effective tool for the proactive identification of hazards for General Aviation. Firstly, this paper introduced the concept of FDA and its benefit to general aviation, then the basic procedure of FDA is presented. Lastly, through an aircraft engine monitoring case illustrate the significance of FDA to General Aviation.
Aircraft maintenance is a highly regulated, safety critical, complex and competitive industry. There is a need to develop innovative solutions to address process efficiency without compromising safety and quality. This paper presents the case that in order to improve a highly complex system such as aircraft maintenance, it is necessary to develop a comprehensive and ecologically valid model of the operational system, which represents not just what is meant to happen, but what normally happens. This model then provides the backdrop against which to change or improve the system. A performance report, the Blocker Report, specific to aircraft maintenance and related to the model was developed gathering data on anything that ‘blocks’ task or check performance. A Blocker Resolution Process was designed to resolve blockers and improve the current check system. Significant results were obtained for the company in the first trial and implications for safety management systems and hazard identification are discussed.
Statement of Relevance: Aircraft maintenance is a safety critical, complex, competitive industry with a need to develop innovative solutions to address process and safety efficiency. This research addresses this through the development of a comprehensive and ecologically valid model of the system linked with a performance reporting and resolution system.
Predictive maintenance using dynamic probabilistic networks
- D Ozgür-Unlüakm
- T Bilgiç
The Evolution of Flight Data Analysis
- N A H Campbell
N. A. H. Campbell, "The Evolution of Flight Data
Analysis," p. 22.
AircraftTechnology improvements
- P Fonta
P. Fonta et al., "AircraftTechnology improvements,"
ICAO Environ. Rep., 2010.
Channeling Oceans of IoT Data
- P Ta-Shma
P. Ta-Shma, "Channeling Oceans of IoT Data," Spark.tc.
[Online]. Available: http://www.spark.tc/channelingoceans-of-iot-data/.
A380 integrated modular avionics
- J.-B Itier
J.-B. Itier, "A380 integrated modular avionics," in
Proceedings of the ARTIST2 meeting on integrated
modular avionics, 2007, vol. 1, pp. 72-75.
Predictive Maintenance for Aircraft Engines
- S Smith
S. Smith, "Predictive Maintenance for Aircraft Engines,"
Revolutions, 25-May-2016..
Predictive Maintenance Benefits for the Airline Industry
- Ibm Coperation
IBM Coperation, "Predictive Maintenance Benefits for
the Airline Industry." Sep-2014.