Search

With the rapid development of the aviation industry, the utilization rate of a runway is getting higher and higher, and the time that aircrafts use the runway for takeoff and landing is getting less and less. Accidents are prone to occur at this stage, so the wheel brake system that plays a key role at this stage attracts much attention. The safety of the wheel brake system is important to ensure the normal takeoff and landing of aircrafts, minimize the occurrence of brake accidents and ensure the safety of the occupants and aircrafts. However, domestic research on wheel brake system mostly focuses on system design and performance simulation. There is little research on condition monitoring and health assessment of wheel brake system, especially hydraulic brake system. Therefore, based on the analysis of the working principle and flight recording parameters of the wheel brake system, the hysteresis characteristics of the system are found for the first time. The model of the wheel brake system considering the hysteresis characteristics is constructed, a health monitoring method based on Kalman filter is established. The effectiveness of the proposed method is verified by simulation and flight record data.

Aircraft hydraulic system is an important system responsible for capacity transmission, which has a great impact on the safety of aircraft flight mission. Therefore, it is imperative to study the health monitoring and prediction of aircraft hydraulic system and its user systems. In this paper, the hydraulic system and its user systems of a certain type of domestic aircraft are taken as the research object. On the basis of analyzing its working principle and using relevant flight parameters, a health monitoring method of hydraulic system and its user systems based on BP neural network and Support Vector Machine (SVM) algorithm is proposed, thus the health monitoring of the hydraulic system and its user systems of aircraft is realized. Based on health monitoring, Logistic Regression (LR) model and Support Vector Machine Regression (SVR) algorithm are used to predict the change trend of aircraft health mechanism and health state, then the health prediction of aircraft hydraulics and its user systems is realized.

To get sufficient environmental information for a teleoperated unmanned vehicle, a matched image with wide field and high quality image is necessary. Image matching is a key point in image mosaic. And the vast amounts of data and complex calculations make it bottlenecked to get a high speed on mosaicing images. Considering the requirements of real-time image mosaic, a self-adaptive image matching method, considering the priori information on the spatial relationship between images, is proposed in this paper. The overlapping region is used as one of the constraint to reduce the search range during the image matching process. And using the General Purpose Graphic Process Unit (GPGPU) to accelerate complex computations, is becoming a research focus. In this paper, the algorithm of image matching is parallelized based on Compute Unified Device Architecture (CUDA), which is a platform of GPGPU programming. Experiment results show that, compared with the serial scheme on CPU, the efficiency of image mosaicing, implemented with the parallel scheme on Graphic Process Unit (GPU), is improved more than 30 times, with 12.8 frames per second.