Time Series Analysis Methods and Applications for Flight Data

verfasst von: Jianye Zhang, Peng Zhang

Verlag: Springer Berlin Heidelberg

Enthalten in: Springer Professional "Wirtschaft+Technik" , Springer Professional "Technik" , Springer Professional "Wirtschaft"

Einloggen, um Zugang zu erhalten

Über dieses Buch

This book focuses on different facets of flight data analysis, including the basic goals, methods, and implementation techniques. As mass flight data possesses the typical characteristics of time series, the time series analysis methods and their application for flight data have been illustrated from several aspects, such as data filtering, data extension, feature optimization, similarity search, trend monitoring, fault diagnosis, and parameter prediction, etc. An intelligent information-processing platform for flight data has been established to assist in aircraft condition monitoring, training evaluation and scientific maintenance. The book will serve as a reference resource for people working in aviation management and maintenance, as well as researchers and engineers in the fields of data analysis and data mining.

Inhaltsverzeichnis

Frontmatter

Chapter 1. Introduction

Abstract

This chapter provides background information for the contents of this book. It briefly introduces some basic concepts about Flight Data Recorder System (FDRS) and its developments. Meanwhile, it focuses on the status and development trends of flight data application research in assessing flight quality and flight performance, monitoring off-line/on-line equipment status and investigating accidents. Then, the research area and main contents of this book are presented with focus on the flight data as a typical time series.

Jianye Zhang, Peng Zhang

Chapter 2. Preprocessing of Flight Data

Abstract

Research findings indicate that the amount, accuracy, and type of data collected from airborne FDRS can hardly meet the requirements for further application and development of flight data. Therefore, it is necessary and fundamental to preprocess original flight data. The level of accuracy and reliability of preprocessing results will have a direct bearing on the quality of follow-on research. This chapter covers outlier elimination, data filling, data extension, reduction of monitorable parameters and chaotic property analysis.

Jianye Zhang, Peng Zhang

Chapter 3. Typical Time Series Analysis of Flight Data Based on ARMA Model

Abstract

Since flight data is a typical time series, time series analysis of flight data processing is a basic and commonly practiced research method. This chapter begins with an introduction to a general modeling method for time series; then an aircraft steady-state parameter prediction method based on AR model is proposed; and finally the method is verified by real flight data.

Jianye Zhang, Peng Zhang

Chapter 4. Similarity Search for Flight Data

Abstract

Similarity search can be used in search of data necessary for model training, and is therefore, an important part of information mining. Since flight data presents itself as a typical time series, for aircraft and its subsystems in similar operating modes or flight conditions, there should be series sets with similar change trends. By means of searching data series with similar features, similarity search provides technological support for flight data research and “mines out” information of empirical values and their underlying rules, thus laying down a solid basis for flight data reconstruction and monitoring of aircraft conditions. Due to the insufficiency of the traditional method of point-to-point comparison, this chapter will elaborate on unary similarity search of flight data in relation to slope distance, angle distance, and curvature distance. In this chapter, the method of multivariable-series-oriented similarity search will also be introduced. This method, verified by real flight data, makes use of variable step length curve binning and QR decomposition of incidence matrix.

Jianye Zhang, Peng Zhang

Chapter 5. Condition Monitoring and Trend Prediction Based on Flight Data

Abstract

This chapter is an introduction to the methods of aircraft condition monitoring, and an elaboration of the diagnostic methods of gradual and abrupt faults based on expert system and dynamic principle component analysis. The monitoring methods introduced here are based on flexible-size grid technology, weighted least squares support vector machine and chaos theory. Both the monitoring and diagnostic methods are verified by using real data.

Jianye Zhang, Peng Zhang

Chapter 6. Design and Implementation of Flight Data Mining System

Abstract

In this chapter, a flight-data-based prototype system of data mining is designed and proposed, which is an instance of practical application of the research findings of the present study in this book. The prototype system takes advantage of the current flight data processing systems and their engineering applications, making effective use of applicable data mining systems, DBMiner for instance. It is capable of performing data query and statistics, as well as “mining out” patterns of time series. Data patterns to be mined out include those of operation conditions of aircraft parts and units and aircraft maneuverings. In addition to being capable of condition monitoring and predicating, and in particular, it works very well in engine health and trend prediction, and therefore promises a wide range of application.

Jianye Zhang, Peng Zhang

Backmatter

Titel: Time Series Analysis Methods and Applications for Flight Data
verfasst von: Jianye Zhang
Peng Zhang
Verlag: Springer Berlin Heidelberg
Electronic ISBN: 978-3-662-53430-4
Print ISBN: 978-3-662-53428-1
DOI: https://doi.org/10.1007/978-3-662-53430-4

Springer Professional

Über dieses Buch

Inhaltsverzeichnis

Frontmatter

Chapter 1. Introduction

Chapter 2. Preprocessing of Flight Data

Chapter 3. Typical Time Series Analysis of Flight Data Based on ARMA Model

Chapter 4. Similarity Search for Flight Data

Chapter 5. Condition Monitoring and Trend Prediction Based on Flight Data

Chapter 6. Design and Implementation of Flight Data Mining System

Backmatter

Premium Partner