Foreign Object Debris Detection System Research Articles

Foreign Object Debris detection system using GoogLeNet

Foreign Object Debris detection system using GoogLeNet

Material Recognition of Foreign Object Debris using Deep Learning

Foreign Object Debris (FOD) is defined as one of the major problems in the airline maintenance industry, reducing the levels of safety. A foreign object which may result in causing serious damage to an airplane, including engine problems and personal safety risks. Therefore, it is critical to detect FOD in place to guarantee the safety of airplanes flying. FOD detection systems in the past lacked an effective method for automatic material recognition as well as high speed and accuracy in detecting materials. This paper proposes the FOD model using a variety of feature extraction approaches like Gray-level Co-occurrence Matrix (GLCM) and Linear Discriminant Analysis (LDA) to extract features and Deep Learning (DL) for classification. The data for this research was taken from the Shanghai Hongqiao International Airport runways. FOD has been done via utilizing a Convolutional Neural Network Classifier (CNN) with 27 layers. Those layers are distributed as follows: nine convolutional layers of type 1D; eight leaky ReLU layers; seven maxpooling 1D layers; two fully connected layers that are represented by the (Dense); and one flattening layer. The performance measures utilized in the system are precision, accuracy, F-score, and recall. The experimental results obtained after implementation and testing are of accuracy 99.8%, precision 100%, recall 100%, and F1-score is 100%. Experiments show that the proposed method has good performance in detection accuracy.

Sound-Based Intelligent Detection of FOD in the Final Assembly of Rocket Tanks

The traditional method of relying on human hearing to detect foreign object debris (FOD) events during rocket tank assembly processes has the limitation of strong reliance on humans and difficulty in establishing objective detection records. This can lead to undetected FOD entering the engine with the fuel and causing major launch accidents. In this study, we developed an automatic, intelligent FOD detection system for rocket tanks based on sound signals to overcome the drawbacks of manual detection, enabling us to take action to prevent accidents in advance. First, we used log-Mel transformation to reduce the high sampling rate of the sound signal. Furthermore, we proposed a multiscale convolution and temporal convolutional network (MS-CTCN) to overcome the challenges of multi-scale temporal feature extraction to detect suspicious FOD events. Finally, we used the proposed post-processing strategies of label smoothing and threshold discrimination to refine the results of FOD event detection and ultimately determine the presence of FOD. The proposed method was validated through FOD experiments. The results showed that the method had an accuracy rate of 99.16% in detecting FOD and had a better potential to prevent accidents compared to the baseline method.

Foreign Object Debris (FOD) Classification Through Material Recognition Using Deep Convolutional Neural Network With Focus on Metal

Foreign object debris (FOD) is any undesired and unintended object placed or found in the specific vicinity of an aircraft (runway/ taxiway) that can cause damage to aircraft or harm personnel on board such as twisted metal strips, screws, nuts, and bolts, depleted concrete runway pieces, stones, pebbles and stationery items. To avoid FOD damages, all airport/ aviation organizations have deployed some sort of FOD prevention procedure. However, automatic FOD detection systems are still scarce owing to the inevitable reliance on human experts that lead to unavoidable human errors. Around 60% of FOD consists of metal which is the most deteriorating for an aircraft. Therefore, the implementation of material recognition techniques for FOD classification through Deep Convolutional Neural Networks (DCNN) is more important than FOD object detection as FOD could be of any shape, size or color. This paper developed a DCNN algorithm for FOD material classification with high accuracy for all included material classes (i.e., metal, concrete, plastic) in general and metal in particular. For this, a new dataset is introduced that consists of 2481 images taken on an operational airport runway in varying illumination and weather conditions. Through extensive testing, it was found that InceptionV3 is the best performing model with 18% improvement in metal recognition, and 11% improvement in average accuracy for all included classes.

Human-assisted robotic detection of foreign object debris inside confined spaces of marine vessels using probabilistic mapping

Many complex vehicular systems, such as large marine vessels, contain confined spaces like water tanks, which are critical for the safe functioning of the vehicles. It is particularly hazardous for humans to inspect such spaces due to limited accessibility, poor visibility, and unstructured configuration. While robots provide a viable alternative, they encounter the same set of challenges in realizing robust autonomy. In this work, we specifically address the problem of detecting foreign object debris (FODs) left inside the confined spaces using a visual mapping-based system that relies on Mahalanobis distance-driven comparisons between the nominal and online maps for local outlier identification. The identified outliers, corresponding to candidate FODs, are used to generate waypoints that are fed to a mobile ground robot to take camera photos. The photos are subsequently labeled by humans for final identification of the presence and types of FODs, leading to high detection accuracy while mitigating the effect of recall–precision tradeoff. Preliminary simulation studies, followed by extensive physical trials on a prototype tank, demonstrate the capability and potential of our FOD detection system.

Airport Runway Foreign Object Debris Detection System Based on Arc-Scanning SAR Technology

Due to the small size of foreign object debris (FOD) and varied complex weather conditions, the detection of FOD on airport runways is a great challenge. Radar is an important method for detecting FOD targets. However, almost all the existing systems are based on real apertures, which have disadvantages such as low azimuth resolution and susceptibility to rain interference. Here, an innovative FOD detection radar system based on arc-scanning synthetic aperture radar (AS-SAR) technology, the AS-SAR based FOD detection system (AS-FODR), achieves omnidirectional coverage with a very high azimuth resolution and the suppression of flicker clutter, such as rain drops in severe weather. According to the radar imaging simulation of a scene under rainy conditions and the information processing analysis of field experiments, a prototype system was built, and an efficient data process flow was proposed. In short, a one centimeter FOD target was detected on the runway more than 250 m away, proving that the use of AS-FODR is feasible and effective.

인공지능 기반 전시 활주로의 불발탄 및 폭파구 정량화에 관한 연구

At the beginning of the war, the runway of a military airfield becomes the top target for enemy missile strikes, and crater of various sizes are formed on the attacked runway, while many unexploded ordnance bombs remain. According to the existing airfield damage analysis technology to solve this problem, manual survey of unexploded ordnance and crater by reconnaissance team relying on visual observation and measuring tape measure, transmission of information about the size and location of crater by radio to the facility control room, and detonation by the facility control room Classification of old buildings, manual selection of MOS, and runway repair (damage restoration) process by the damage recovery team are sequential is done. However, the existing technology takes a long time to work due to the manual surveying of unexploded ordnance munitions and crater, and there is a high possibility that the reference point will be lost. There is a problem, and there is a possibility of secondary work by the information morning moon in the runway repair process. A fixed FOD(Foreign Object Debris) detection system can be applied to solve this visual inspection problem, but there is a problem in that the installation of a fixed tower itself is not preferred around the runway due to flight safety issues. This study is proposed to solve the above problems, and based on drone footage, artificial intelligence algorithm, and SfM(Structure from Motion) algorithm for point cloud generation, it is possible to analyze the damage at the emergency airfield in wartime and to develop an automated system for repairing damage to the flight pavement. Its purpose is to develop.

Line of sight visibility analysis for foreign object debris detection system

It is challenging to monitor busy airports’ runway through visual inspection to precisely detect foreign object debris. Currently, many technologies for the detection of foreign object debris are available. It has been investigated that millimeter-wave radar technology’s detection capability can be one of the most effective techniques for detecting foreign object debris as it is weather-resilient. However, the positioning and height of a millimeter-wave radar pole covering the runway area, considering the existing runway infrastructure, are challenging. The task involves finding the appropriate placement and optimum height. This paper presents a novel method of line of sight visibility for placement and height of radar pole using human factor research to ensure that each point on the runway is visible from various heights of the millimeter-wave radar pole to the runway locations. Kuala Lumpur International Airport, Malaysia runway 32L/14R, has used a case study to test the visibility analysis. The visual analytic test’s successful results for different millimeter-wave radar pole locations and viewing heights under a visible and invisible line of sight conditions on the runway have been verified in the field experiment.

A FOD Detection Approach on Millimeter-Wave Radar Sensors Based on Optimal VMD and SVDD

Foreign object debris (FOD) on airport runways can cause serious accidents and huge economic losses. FOD detection systems based on millimeter-wave (MMW) radar sensors have the advantages of higher range resolution and lower power consumption. However, it is difficult for traditional FOD detection methods to detect and distinguish weak signals of targets from strong ground clutter. To solve this problem, this paper proposes a new FOD detection approach based on optimized variational mode decomposition (VMD) and support vector data description (SVDD). This approach utilizes SVDD as a classifier to distinguish FOD signals from clutter signals. More importantly, the VMD optimized by whale optimization algorithm (WOA) is used to improve the accuracy and stability of the classifier. The results from both the simulation and field case show the excellent FOD detection performance of the proposed VMD-SVDD method.

Demonstration of Airport Runway FOD Detection System Based On Vehicle SAR

In the background of detecting Foreign Object Debris (FOD) on the airport runway with conventional radar systems or optical systems, to solve the problems that the current detection technology of conventional radar is high frequency and high cost, and the optical system is vulnerable to environmental factors, this paper uses linear frequency modulated continuous wave (LFM-CW) signal in Ka band to detect FOD based on the Synthetic Aperture Radar (SAR) airport runway FOD detection system. Firstly, it is proved that the operating frequency of 36GHz is more suitable. Then demonstration that the use of LFM-CW can effectively reduce the system power. Finally, through the demonstration of the main technical indicators of the system, it is proved that the airport runway FOD detection system based on vehicle SAR can effectively detect objects with a height of 3cm and a cross-sectional area of 0.00051m2 in a distance of 210 meters when the transmitting power is 25dBm and the running speed is 61.2m/s. At this time, the detection probability is 0.9999 and the false alarm rate is 10−12.

Foreign object debris material recognition based on convolutional neural networks

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.

Millimeter-Wave Radio-Over-Fiber Network for Linear Cell Systems

We discuss and propose millimeter-wave linear cell systems for signal distribution on railway radiocommunication systems between train and trackside, and a foreign object debris detection system for airport runways using the radio-over-fiber network technology. Linear cell configurations based on wavelength-division multiplexing (WDM) and power-splitter-based distribution networks are discussed and demonstrated experimentally. A single-sideband modulation for data transmission in an intermediate frequency over a fiber system is successfully transmitted with an ultrafast wavelength-tunable laser diode for WDM routing to track the train car within 3 $\mu$ s. Radar signal distribution by an optical double-sideband suppressed-carrier modulation mitigates the dispersion effect of the fiber cable to transmit a 32-GHz signal into the remote radar heads.

Airport Runway FOD Detection from LFMCW Radar and Image Data

Airport runway Foreign Object Debris (FOD) jeopardizes flight safety and leads to a large amount of financial cost on flight maintenance constantly. Several FOD detection systems based on a variety of detection techniques and architectures have been developed. This paper gives a brief introduction of our FOD detection system, in comparison with FOD detection systems currently in the international market. What distinguish our system from all the others is that, our detection approach is based on both linear frequency modulated continuous wave (LFMCW) radar signal and image data. This innovation combines the advantages of radar in shape detection and image in appearance detection. As a result, it increases the FOD detection rate and reduces the false alarming rate. Experiments following Federal Aviation Administration (FAA) advisory indicate that our system has reached the FAA requirements.

활주로 FOD 탐지 효율화를 위한 기술적 고찰

FOD(Foreign Object Debris) has the potential threat to damage aircraft during critical phases of take-off and landing roll with some objects including metal on the runway. FOD can be found anywhere on an airport's air operation areas such as runway, taxiway and apron. It can lead to catastrophic loss of life and airframe, and increased maintenance and operating costs. In this paper, we defined FOD and surveyed its riskiness and necessity of automatic FOD detection system. We compared the requirements of the environment in Korea to the FAA advisory circular. Also we analyzed operation methods of FOD detection systems already installed at some airports. Based on the surveys mentioned above, we propose hybrid type of FOD detection system considering the environment in Korea which uses millimeter wave radar, optical camera and thermal imaging camera to detect FOD efficiently. In management approach, fixed type of the system should be installed for real-time monitoring, and mobile type of the system can be used additionally.

Research and Design of an Airfield Runway FOD Detection System Based on WSN

Foreign object debris (FOD) would potentially cause huge damage when it appears on the airport runway, so the FOD surveillance system is one of the essential protectors for airplane's safety now. This paper introduces a designed method of airport runway FOD detection system based on WSN, analyzes function of various image acquisition sensors, and introduces FOD image analysis algorithm. Finally WSN data fusion technology is used to analyze the FOD image.

76.5 GHz millimeter-wave radar for foreign objects debris detection on airport runways

The paper is a joint work between the LEAT (France) and the ENRI (Japan) in the framework of a Sakura project supported by the JSPS and the French Ministry of Foreign Affairs. The purpose is the study of a FOD (Foreign Object Debris) detection system on airport runways. An FM-CW mm-wave radar working between 76.25 and 76.75 GHz is used together with a high directivity printed reflectarray. In addition, a second measurement campaign has been conducted with a 73.8–79.8 GHz (6 GHz band) radar. Measurement results show detection capabilities of a −20 dBsm cylinder up to 35 m that is 10 m less than the FAA recommendations. Antenna improvements are discussed for reaching the requirements and system performance as well as the use of calibration objects.