Feng Songlin

Bio: Feng Songlin is an academic researcher from Chinese Academy of Sciences. The author has contributed to research in topics: Data processing & Mobile computing. The author has an hindex of 3, co-authored 6 publications receiving 36 citations.

Foreign object debris material recognition based on convolutional neural networks

Abstract: The material attributes of foreign object debris (FOD) are the most crucial factors to understand the level of damage sustained by an aircraft. However, the prevalent FOD detection systems lack an effective method for automatic material recognition. This paper proposes a novel FOD material recognition approach based on both transfer learning and a mainstream deep convolutional neural network (D-CNN) model. To this end, we create an FOD image dataset consisting of images from the runways of Shanghai Hongqiao International Airport and the campus of our research institute. We optimize the architecture of the D-CNN by considering the characteristics of the material distribution of the FOD. The results show that the proposed approach can improve the accuracy of material recognition by 39.6% over the state-of-the-art method. The work here will help enhance the intelligence capability of future FOD detection systems and encourage other practical applications of material recognition technology.

Object material identification method based on multi-sensor information fusion

Abstract: The invention provides an object material identification method based on multi-sensor information fusion. The method comprises steps: firstly, at least three kinds of sensors are provided; then, the sensors are used for transmitting source signals to a to-be-identified object, feature signals transmitted by the to-be-identified object under irradiation of the source signals are acquired respectively, or the sensors are directly used for acquiring the feature signals of the to-be-identified object, and object material information provided by each feature signal is extracted; and finally, the information is analyzed comprehensively to determine the material of the object. According to the object material identification method of the invention, data complementation and redundancy of different sensors are used, information is acquired from each independent piece of measurement space, the target object material can be identified through a fusion technology, the detection accuracy is high, and reliable data are provided for object material identification.

Classified corpus establishing method and system and server provided with system

Abstract: The invention provides a classified corpus establishing method and system and a server provided with the system. The establishing method comprises the steps of acquiring target data to be classified and acquiring category description data according to actual needs, selecting a text similarity calculating method corresponding to maximum accuracy, classifying the target data to be classified as a category corresponding to maximum similarity, filling the target data with first classification matching degree within a first similarity range in a preset primary corpus, classifying the rest of the target data to be classified with a selected and well trained classifier, filling the target data with second classification matching degree within a second similarity range in the preset primary corpus, and determining the preset primary corpus as a final corpus when the filled preset primary corpus can not be enlarged any more. In this way, corpus establishment cost is reduced, manual intervene degree is reduced, and corpus establishment time is shortened.

Unmanned aerial vehicle intrusion interception method and device

Abstract: The invention provides an unmanned aerial vehicle (UAV) intrusion interception method and device. The method includes the following steps: when the invasion of a UAV is monitored in a preset area through a space-domain scanning mode, an intrusion signal is immediately transmitted to a frequency-domain scanning mode, and the frequency-domain scanning mode acquires the change of wireless spectrum inthe preset area; the communication frequency of communication between the UAV and control equipment thereof is obtained through analysis according to the change of wireless spectrum; and a preset interference operation is performed on the UAV according to the communication frequency to force the UAV to land, or the permission to control the UAV is obtained according to the communication frequencyto make the UAV land, or the power of the UAV is quickly consumed through a wireless power consuming technology to force the UAV to land. A UAV can be forced to land effectively and accurately, and the landing of the UAV can be controlled without damage by obtaining the control right.

Mobile computing storage device and information processing method for civil aviation industry

Abstract: The present invention provides a mobile computing storage device and information processing method for the civil aviation industry. The device comprises an information processing module which calculates and stores large data quantity information, a synchronization updating system which synchronizes the data in the information processing module to a data center and updates the processing function of the information processing module for the information through the data center, a communication module which realizes data transmission through wireless transmission, a detection mobile module which detects the performance of a wireless signal and moves to a maintenance portable mobile terminal when the performance of the wireless signal is decreased, and a power supply module. The mobile computing storage device for the civil aviation industry is arranged between the data center and the maintenance portable mobile terminal, provides large data quantity information processing and storage services through wireless communication, and sends a calculation result to the maintenance portable mobile terminal. When the data center is connected, the data is synchronized to the data center. According to the mobile computing storage device and the information processing method for the civil aviation industry, the data processing ability of a civil aviation maintenance field is greatly improved, and the maintenance cost is reduced.

Convolutional neural network: a review of models, methodologies and applications to object detection

Abstract: Deep learning has developed as an effective machine learning method that takes in numerous layers of features or representation of the data and provides state-of-the-art results. The application of deep learning has shown impressive performance in various application areas, particularly in image classification, segmentation and object detection. Recent advances of deep learning techniques bring encouraging performance to fine-grained image classification which aims to distinguish subordinate-level categories. This task is extremely challenging due to high intra-class and low inter-class variance. In this paper, we provide a detailed review of various deep architectures and model highlighting characteristics of particular model. Firstly, we described the functioning of CNN architectures and its components followed by detailed description of various CNN models starting with classical LeNet model to AlexNet, ZFNet, GoogleNet, VGGNet, ResNet, ResNeXt, SENet, DenseNet, Xception, PNAS/ENAS. We mainly focus on the application of deep learning architectures to three major applications, namely (i) wild animal detection, (ii) small arm detection and (iii) human being detection. A detailed review summary including the systems, database, application and accuracy claimed is also provided for each model to serve as guidelines for future work in the above application areas.

Leading edge topography of blades - a critical review

Abstract: In turbomachinery, their blade leading edges are critical to performance and therefore fuel efficiency, emission, noise, running and maintenance costs. Leading edge damage and therefore roughness is either caused by subtractive processes such as foreign object damage (bird strikes and debris ingestion) and erosion (hail, rain droplets, sand particles, dust, volcanic ash and cavitation) and additive processes such as filming (from dirt, icing, fouling, insect build-up). Therefore, this review focuses on the changes in topography induced by during service to blade leading edges and the effect of roughness and form on performance and efforts to predict and model these changes. The applications considered are focused on wind, gas and tidal turbines and turbofan engines. Repair and protection strategies for leading edges of blades are also reviewed. The review shows additive processes are typically worse than subtractive processes, as the roughness or even form change is significant with icing and biofouling. Antagonism is reported between additive and subtractive roughness processes. There are gaps in the current understanding of the additive and subtractive processes that influence roughness and their interaction. Recent work paves the way forward where modelling and machine learning is used to predict coated wind turbine blade leading edge delamination and the effects this has on aerodynamic performance and what changes in blade angle would best capture the available wind energy with such damaged blades. To do this generically there is a need for better understanding of the environment that the blades see and the variation along their length, the material or coated material response to additive and/or subtractive mechanisms and thus the roughness/form evolution over time. This is turn would allow better understanding of the effects these changes have on aerodynamic/ hydrodynamic efficiency and the population of stress raisers and distribution of residual stresses that result. These in turn influence fatigue strength and remaining useful life of the blade leading edge as well as inform maintenance/repair needs

A Sequential CNN Approach for Foreign Object Detection in Hyperspectral Images

Abstract: This paper reports about potentials of hyperspectral imaging for object detection, especially on an application of foreign object detection (FOD) in meat products. A sequential deep-learning framework is proposed by using region-proposal networks (RPNs) and 3D convolutional networks (CNNs). Two independent datasets of images, contaminated with many types of foreign materials, were used for training and testing the proposed model. Results show that the proposed RPN model outperforms a selected search method in terms of accuracy, efficiency, and run-time. An FOD model based on RPN and 3D-CNN, or selected search with a 3D-CNN solve FOD with an average precision of 81.0% or 50.6%, respectively. This study demonstrates opportunities when using hyperspectral imaging systems for real-time object detection by using both spectral and spatial features combined.

Small Foreign Object Debris Detection for Millimeter-Wave Radar Based on Power Spectrum Features

Abstract: Foreign object debris (FOD) detection can be considered a kind of classification that distinguishes the measured signal as either containing FOD targets or only corresponding to ground clutter. In this paper, we propose a support vector domain description (SVDD) classifier with the particle swarm optimization (PSO) algorithm for FOD detection. The echo features of FOD and ground clutter received by the millimeter-wave radar are first extracted in the power spectrum domain as input eigenvectors of the classifier, followed with the parameters optimized by the PSO algorithm, and lastly, a PSO-SVDD classifier is established. However, since only ground clutter samples are utilized to train the SVDD classifier, overfitting inevitably occurs. Thus, a small number of samples with FOD are added in the training stage to further construct a PSO-NSVDD (NSVDD: SVDD with negative examples) classifier to achieve better classification performance. Experimental results based on measured data showed that the proposed methods could not only achieve a good detection performance but also significantly reduce the false alarm rate.