Haixia Su

A integrated vehicle health management framework for aircraft — A preliminary report

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.

Civil Aircraft Big Data Platform

The aviation industry generates massive data every day. By analyzing the aviation big data, aviation manufacturers and airlines can optimize the flight of civil aircraft including risk reducing, operation optimization, and personalized services. Building a platform for storing and analyzing the aviation big data becomes an important task for civil aviation. This paper proposes a civil aircraft big data platform that works on facilitate the development of civil aviation. The platform collects data from multiple types of data sources, including aircrafts, airlines, and maintenance centers. The platform provides decision making support for civil aircrafts including maintenance plan, real-time alarm, health management, fuel saving, and airline schedule. The paper introduces the architecture of the platform and present applications to show how the platform facilitates civil aviation.

Big Data Collection and Analysis Framework Research for Public Digital Culture Sharing Service

The big data collection and analysis of public digital culture sharing service is researched in this paper. Big data includes three types of data, namely: ancillary service data, public digital culture sharing service platform operation data and user data. The aim is to build a data analysis platform for the three classes of data. Through the analysis of the three types of data collected, the use of resources and the operation of the platform can be mastered for providing better service for resource organization and scheduling of platform. Through the analysis of three types of the collected data, it can realize all kinds of statistics and analysis services in multidimensional. This paper presents a personalized recommender system of public digital cultural resources.

A fault diagnosis method of engine rotor based on Random Forests

Rotor is the main part of the engine, the vibration fault is very common in the process of running, it must be monitored, checked, excluded in a timely manner for improving the reliability of engine and aircraft safety. This paper mainly studies four kinds of rotor fault, including unbalance, misalignment, surge, bearing failure. The frequency spectrum of the vibration signal of a rotor system is an important basis for rotor fault diagnosis, using the spectrum of rotor to build decision tree analysis is an important method for rotor fault detection. As the single decision trees anti-interference ability is very poor, this paper presents an engine rotor fault diagnosis method based on Random Forests. Experimental results show that the accuracy of this diagnosis method is high, the failures can be diagnosed timely and effectively to keep the engine in normal operation. To evaluate the validity of Random Forests, a SVM classifier is trained for comparison. Compare with SVM, we obtain better classification in Random Forests algorithm. This result demonstrates that Random Forests algorithm is a valid method for engine rotor.

Parameters modeling and fault simulation for flight control system based on SIMULINK

The establishment of flight control system parameters modeling and fault simulation is the basis of fault diagnosis. In this paper, the flight control system simulation model is established by MATLAB / SIMULINK. We describe the modules and implementation methods of the flight control system parameters modeling in detail. In addition, the simulation of the failure mode and realization is introduced. Finally, we do some simulations and make some analysis to the simulation results. The simulation results show that our methods are well.

Fault feature analysis of civil aircraft control surface damage

This paper analyzes the control surface damage of civil aircraft flight control system. Firstly, the fault feature extraction method is analyzed. Then the control surface damage is studied and it is simulated by Simulink. The fault injection is realized by setting the damage coefficient in the simulation model. It simulates seven kinds of fault modes, analyzes the simulated flight data in time domain, then getting the typical fault feature set of flight control system. At last, taking the elevator control surface damage as an example, this paper analyzes the fault characteristics of the civil aircraft flight control system. The results show that the method has good practicability.

A prediction method for aero-engine health management based on nonlinear time series analysis

Aero-engine is the heart of the aircraft. If a failure of aero-engine occurs during the flight, it will be a direct threat to flight safety of the aircraft, so the aero-engine health management came into being, and the prediction is a very important part of it. This paper was focused on the prediction methods of health management. Firstly, we introduced the research status of the aero-engine prediction methods, and then proposed a prediction method of nonlinear time series analysis using C-C method and BP-Adaboost algorithm, at last, a simulation example was given to illustrate the validity of the method. Experimental results indicated that the method has the advantage of high prediction precision, and to some extent, it can provide a reference for the maintenance plan.

A Study of Chinese Character Culture Big Data Platform

Chinese Characters are important elements of Chinese culture. Digitization techniques of Chinese Characters introduce attractive experiences of Chinese Character culture. The Chinese Character digitization generates large-scale data that is hard handled by traditional methods. To address this issue, in this paper, we propose Chinese Character Culture Big Data Platform that is designed based on the three-level hierarchy of cloud computing. The platform is built by means of open source technologies, for example, Hadoop ecosystem. The platform can effectively store, manage, and analyze large-scale data of digitized Chinese Character for supporting the Chinese Character culture experience application systems. This paper presents design concepts and architecture of the platform, as well as an experiment.

Simulation and fault diagnosis for aviation engine starting system based on SIMULINK

According to the characteristics of aviation engine starting process, this paper mainly analyzes state parameters of the starting process, and establishes its mathematical model. On the basis of using the SIMULINK to simulate aviation engine starting system, some fault conditions are tested to obtain fault data, and the principal component analysis (PCA) is used for data dimension reduction and to obtain the characteristic data by MATLAB. Then the genetic algorithm is used to optimize the back propagation (BP) neural network training features, and finally with test data to verify the accuracy of the results. Diagnostic results indicates that the complexity of the neural network structure and the training time are both reduced, and the accuracy of diagnosis is improved by the genetic algorithm combined with BP algorithm (GA-BP).