Search

Onboard, real-time object detection in unmaned aerial vehicle remote sensing (UAV-RS) has always been a prominent challenge due to the higher image resolution required and the limited computing resources available. Due to the trade-off between accuracy and efficiency, the advantages of UAV-RS are difficult to fully exploit. Current sparse-convolution-based detectors only convolve some of the meaningful features in order to accelerate the inference speed. However, the best approach to the selection of meaningful features, which ultimately determines the performance, is an open question. This study proposes the use of adaptive sparse convolutional networks based on class maps for real-time onboard detection in UAV-RS images (SCCMDet) to solve this problem. For data pre-processing, SCCMDet obtains the real class maps as labels from the ground truth to supervise the feature selection process. In addition, a generate class map network (GCMN), equipped with a newly designed loss function, identifies the importance of features to generate a binary class map which filters the image for its more meaningful sparse features. Comparative experiments were conducted on the VisDrone dataset, and the experimental results show that our method accelerates YOLOv8 by 41.94% at most and increases the performance by 2.52%. Moreover, ablation experiments demonstrate the effectiveness of the proposed model. [ABSTRACT FROM AUTHOR]

Edge computing enables rapid data processing and decision-making on satellite payloads. Deploying deep learning-based techniques for low-light image enhancement improves early detection and tracking accuracy on satellite platforms, but it faces challenges due to limited computational resources. This article proposes an edge-computing-enabled inference model specifically designed onboard satellites. The proposed model follows an encoder–decoder architecture to generate the illumination map with low multiplication matrix complexity, 25.52 GMac of $1920 \times 1200$ image size. To reduce nanosatellite hardware consumption with a single-precision floating-point format, the edge-computing-enabled inference model proposes a quantized convolution that computes signed values. The proposed inference model is deployed on Arm Cortex-M3 microcontrollers onboard satellite payload (86.74 times faster than normal convolution model) but also has a similar quality with the low-light enhanced in full-precision computing of lightweight training model by using the peak signal-to-noise ratio (average of 28.94) and structural similarity index (average of 0.85) metrics.

Onboard real-time processing of remote sensing satellites is an important means of rapidly obtaining information, and the fusion processing of panchromatic and multispectral data is of great significance for optical satellites. In order to ensure the effect, most traditional algorithms perform statistical analysis or transformation on the entire image first and then perform subsequent processing. There are problems such as high algorithm complexity and resource occupation, and it is difficult to apply to onboard scenarios where the volume and power consumption are strictly limited. Aiming at the requirements of onboard fusion, a real-time processing approach for high-resolution optical satellites is proposed. First, through the implementation of real-time geometric positioning, ROI extraction is completed while the camera is imaging, avoiding the disadvantages of traditional methods for processing large amounts of data; then, based on the principle of object-space consistency, by fine-tuning virtual sensor parameters, the registration of a panchromatic multispectral image is completed in the sensor correction step, so that the relative accuracy of the two can meet the fusion requirements, and time-consuming pixel-level registration processing is avoided; finally, according to the characteristics of the algorithms and embedded hardware, an efficient algorithm mapping strategy is formulated, and deep optimization is implemented to achieve a significant improvement in performance. Experiments show that the performance of this method is improved by 156.23 times compared with the traditional method. Moreover, after building a parallel pipeline, it can meet the real-time fusion processing requirement of completing a 5000 × 5000 pixels ROI area every 2.4 s.

Onboard determination of state-of-health (SoH) parameters becomes increasingly important with tightened lifetime requirements for automotive polymer electrolyte membrane (PEM) fuel cell systems. One way to electrochemically characterize SoH parameters like active catalyst surface area (roughness factor, RF), double layer capacitance and membrane permeability is the nitrogen-flush-requiring Galvanostatic Charge Method (GCM). In this publication, a nitrogen-flush-free and thus, onboard-compatible adapted version of GCM (AGCM from Möller et al. (2023)), is directly compared to its original method, GCM. A 20-cell automotive shortstack was frequently characterized with both GCM and AGCM methods as well as standard Cyclic Voltammetry (CV) during a degradation test. Additionally, the evaluation model for AGCM was varied in two aspects: Firstly, modeling the hydrogen partial pressure difference (Δ p H 2 ) responsible for hydrogen crossover and secondly, modeling hydrogen diffusion in the cathode volume with a 0-D transport model. The characterization results prove that all investigated model variations of AGCM can reproduce double layer capacitance results from GCM and CV, as well as the decreasing trend in roughness factor results. RF-values characterized by AGCM agree with either GCM or CV results, depending on the evaluation model. A thorough analysis revealed the neglected short circuit resistance in combination with the chosen modeling approach of Δ p H 2 in AGCM as the reason. The two modeling approaches for Δ p H 2 base on extreme assumptions about the homogeneity of hydrogen distribution in the anode volume. Neither of them could reproduce the membrane permeability of GCM. Instead, one overestimates, one underestimates it, indicating the truth to be in between the two extreme models. However, AGCM measurement conditions are identified as a lever to improve the AGCM permeability results and their robustness, even if the modeling approaches remain unchanged. Furthermore, this study showed that neglecting hydrogen diffusion in the cathode volume in the AGCM evaluation model leads to overestimation of the membrane permeability. [Display omitted] • Experimental comparison of GCM with and without nitrogen flush. • Modeling of H 2 partial pressure difference influences roughness factor results. • Adding H 2 diffusion to AGCM evaluation improves result precision. • Measurement conditions can be adapted to increase result robustness. [ABSTRACT FROM AUTHOR]

The existing aeroengine instability precursor detection methods can be summarized as applying advanced signal processing technologies to various signals from the compressor test rig rather than the whole engine. Besides, these methods seriously depend on the artificial designed feature and threshold and also ignore the limit on the sensors onboard. Thus, with the help of the powerful feature extraction ability of the deep neural network, a real-time surge prediction method based on the multi-branch feature fusion neural network (MBFFNN) is proposed. First, the dataset can be obtained by using overlapping slices to divide surge test data into a sample sequence and using complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) to label each sample precisely. Second, for each sample, the time-domain statistical parameters are calculated and the recurrence plot is obtained by using phase space reconstruction. Finally, the MBFFNN with mixed data type input is designed, and its performance is evaluated by the generated dataset. The experimental results show that compared with multilayer perceptron (MLP), long short-term memory (LSTM), and deep residual network (DRN), MBFFNN has the best performance on two datasets for different surge tests, which demonstrates that the proposed method for surge prediction can accurately judge the state of the aeroengine, identify the instability precursor before the surge, and give an early warning in advance. [ABSTRACT FROM AUTHOR]

This paper presents the ONCLE (One Clock Ensemble) solution for the Galileo time and frequency reference system with advanced features in terms of robustness, performance, continuity, and simplicity. Each component clock is frequency-steered to the ensemble time, which itself creates an average of those steered clock outputs, while clock faults are detected and corrected in real time within an integrated system. The feasibility of algorithm and hardware approaches has been demonstrated on an elegant breadboard and verified by an extended test and validation campaign at the Engineering Model (EM) level, developed for the Galileo next-generation onboard timing system under European GNSS Evolutions Program. Based on the progress for space application and the heritage on the Galileo ground precise timing facility (PTF), we propose a robust solution for the upgrade of PTF for ground application aiming to provide a fully continuous and performance-improved timescale under automated operation. The capability is demonstrated by preliminary simulation results. [ABSTRACT FROM AUTHOR]

The increasing functionality and complexity of electronic systems places higher demands on the efficiency of system verification tests. The traditional satellite test platform is customized according to the specific model task. Its design and development cycle is long, and the comprehensive cost is difficult to adapt to the current task requirements. To this end, this paper proposes a general simulation test platform architecture for on-board solid-state storage controller based on System Verilog. It uses a hierarchical model internally, and the signal interface uses APB bus standard uniformly. It can be configured by testing the platform data source and format to adapt to onboard solid-state storage controllers of different capacities, different rates and different configurations. Experiments show that the test platform designed in this paper has certain versatility, which can effectively save test time and improve test coverage compared with traditional test platform.

The modern advanced aero-engine control methods are onboard dynamic model–based algorithms. In this article, a novel aero-engine dynamic modeling method based on improved compact propulsion system dynamic model is proposed. The aero-engine model is divided into inlet, core engine, surge margin and nozzle models for establishing sub-model in the compact propulsion system dynamic model. The model of core engine is state variable model. The models of inlet, surge margin and nozzle are nonlinear models which are similar to the component level model. A new scheduling scheme for basepoint control vector, basepoint state vector and basepoint output vector which considers the change of engine total inlet temperature is proposed to improve engine model accuracy especially the steady. The online feedback correction of measurable parameters is adopted to improve the steady and dynamic accuracy of model. The modeling errors of improved compact propulsion system dynamic model remain unchanged when engine total inlet temperature of different conditions are the same or changes small. The model accuracy of compact propulsion system dynamic model, especially the measurable parameters, is improved by online feedback correction. Moreover, the real-time performance of compact propulsion system dynamic model and improved compact propulsion system dynamic model are much better than component level model. [ABSTRACT FROM AUTHOR]

Because the leaky coaxial cable is mainly laid in the sections with poor wireless signal coverage, such as railway tunnels and curves, and high-speed train operation may cause the wind tunnel eff ect, the leaky cable and fi xed components are easy to cause looseness, falling off and other situations, and there are serious driving safety risks. In this paper, the onboard image intelligent detection system for leakage coaxial cable is studied, and the system is applied to the actual inspection work to improve the detection quality, detection effi ciency and personnel effi ciency. [ABSTRACT FROM AUTHOR]

Image registration is important in geostationary weather satellites. Achieving consistent registration of the images with respect to the geographical locations on the Earth is here of interest. The consistency in the registration between the images is affected whenever the orbital inclination and eccentricity are not zero. The imaging payload has a two-axis scanning mirror to capture the Earth image. The above orbital effects together with scan mirror pointing direction are the factors that cause the misregistration. This paper presents an onboard algorithm that provides the scan compensation angles due to the above factors and achieves consistent registration. The compensation varies every second, which is the time taken for each scan. Hence it is preferred to have computations onboard than to have ground based bulk uplinks for the scan compensation. The paper presents an algorithm that is useful, say, when (i) the onboard computing capabilities are limited, (ii) the navigation accuracies are coarse and (iii) the image resampling is not preferred on the ground and the payload data are directly used for weather applications. The paper also discusses the tests that were carried on the onboard software in order to validate its performance in achieving the consistent registration before launch. This is done by using another independent software tool which is also described in detail. Image motion algorithm was invoked for a couple of days in INSAT 3DR. The atmospheric wind vector deduced directly from the satellite images is given at the end. [ABSTRACT FROM AUTHOR]

Nanosatellites are being widely used in various missions, including remote sensing applications. However, the difficulty lies in mission operation due to downlink speed limitation in nanosatellites. Considering the global cloud fraction of 67%, retrieving clear images through the limited downlink capacity becomes a larger issue. In order to solve this problem, we propose an image prioritization method based on cloud coverage using CNN. The CNN is designed to be lightweight and to be able to prioritize RGB images for nanosatellite application. As previous CNNs are too heavy for onboard processing, new strategies are introduced to lighten the network. The input size is reduced, and patch decomposition is implemented for reduced memory usage. Replication padding is applied on the first block to suppress border ambiguity in the patches. The depth of the network is reduced for small input size adaptation, and the number of kernels is reduced to decrease the total number of parameters. Lastly, a multi-stream architecture is implemented to suppress the network from optimizing on color features. As a result, the number of parameters was reduced down to 0.4%, and the inference time was reduced down to 4.3% of the original network while maintaining approximately 70% precision. We expect that the proposed method will enhance the downlink capability of clear images in nanosatellites by 112%.

Given the constant demand for heavier, longer, faster, and more efficient rail freight vehicles, onboard fault detection systems appear as a good approach for enhanced railway asset exploitation. Real-time condition monitoring reduces inefficient preventive and reactive maintenance actions, decreases waste from replacing parts that still have a useful life, and improves availability and safety by real-time rolling stock diagnosis. There have been considerable advances in wayside monitoring applications, but these cannot achieve real-time continuous monitoring. With the price reduction and miniaturization trends of electronic devices, the cost of deploying wireless sensor networks onboard freight trains continues to become more feasible and accessible. On the other hand, the lack of onboard electric power availability on freight wagons appears as the major limitation for the implementation of these technologies. This paper reviews recent onboard condition monitoring sensors, systems, methods and techniques, aiming to define the present state of the art and its potential application for freight wagons without onboard electric power. [ABSTRACT FROM AUTHOR]

Significant advances in spaceborne imaging payloads have resulted in new big data problems in the Earth Observation (EO) field. These challenges are compounded onboard satellites due to a lack of equivalent advancement in onboard data processing and downlink technologies. We have previously proposed a new GPU accelerated onboard data processing architecture and developed parallelised image processing software to demonstrate the achievable data processing throughput and compression performance. However, the environmental characteristics are distinctly different to those on Earth, such as available power and the probability of adverse single event radiation effects. In this paper, we analyse new performance results for a low power embedded GPU platform, investigate the error resilience of our GPU image processing application and offer two new error resilient versions of the application. We utilise software based error injection testing to evaluate data corruption and functional interrupts. These results inform the new error resilient methods that also leverages GPU characteristics to minimise time and memory overheads. The key results show that our targeted redundancy techniques reduce the data corruption from a probability of up to 46 percent to now less than 2 percent for all test cases, with a typical execution time overhead of 130 percent. [ABSTRACT FROM AUTHOR]

A novel approach to onboard in-flight weight and balance estimation systems is presented. Data from an Airbus A320 fleet from an airline were used to assess the feasibility of the approach. Simple flight mechanics in combination with statistics allowed for the identification of weight and center of gravity position using cruise angle of attack, Mach number and elevator deflection values. The good agreement between the theoretical model and the obtained values for the lift curve slope as a function of Mach as well as the standard error of the estimate for center of gravity position and cruise flying weight indicate that the method is sound. The major implication of this work is that the development of onboard and in-flight weight and balance systems can be significantly simpler than previous literature suggested. The impact of this paper could be immediate for airlines since all the tools required to implement the system as described are readily available. This could have an effect in operating costs, safety and environment. [ABSTRACT FROM AUTHOR]

This paper presents a FPGA-based method for on-board detection and matching of the feature points. With the proposed method, a parallel processing model and a pipeline structure are presented to ensure a high frame rate at processing speed, but with a low power consumption. To save the FPGA resources and increase the processing speed, a model which combines the modified SURF detector and a BRIEF descriptor, is presented as well. Three pairs of images with different land coverages are used to evaluate the performance of FPGA-based implementation. The experiment results demonstrate that (1) when the image pairs with artificial features (such as buildings and roads), the performance of FPGA-based implementation is better than those image pairs with natural features (such as woods); (2) the proposed FPGA-based method is capable of ensuring the processing speed at a high frame rate, such as the speed of can achieve 304 fps under a 100 MHz clock frequency. The speedup of the proposed implementation is about 27 times higher than that when using the PC-based implementation. [ABSTRACT FROM AUTHOR]

The early detection of faults in rolling stock wheels and axle bearings is of paramount importance for rail infrastructure managers as it contributes to the safety of rail operations. In this paper we report on the key results that have arisen from the development and implementation of a novel condition monitoring system based on high-frequency acoustic emission and vibration analysis installed on a train. The novel system makes use of inexpensive and robust acoustic emission sensors and accelerometers, which can be easily installed on the axle bearing box with minimal intervention required. Experimental work carried out under actual conditions at the Long Marston rail track and on the Lisbon – Cas-Cais suburban line has proven that the developed system is capable of detecting wheel and axle bearing-related defects with various levels of severity. [ABSTRACT FROM AUTHOR]

Purpose: To construct a robotic SPECT system and to demonstrate its capability to image a thorax phantom on a radiation therapy flat-top couch, as a step toward onboard functional and molecular imaging in radiation therapy. Methods: A robotic SPECT imaging system was constructed utilizing a gamma camera detector (Digirad 2020tc) and a robot (KUKA KR150 L110 robot). An imaging study was performed with a phantom (PET CT Phantom™), which includes five spheres of 10, 13, 17, 22, and 28 mm diameters. The phantom was placed on a flat-top couch. SPECT projections were acquired either with a parallel-hole collimator or a single-pinhole collimator, both without background in the phantom and with background at 1/10th the sphere activity concentration. The imaging trajectories of parallel-hole and pinhole collimated detectors spanned 180° and 228°, respectively. The pinhole detector viewed an off-centered spherical common volume which encompassed the 28 and 22 mm spheres. The common volume for parallel-hole system was centered at the phantom which encompassed all five spheres in the phantom. The maneuverability of the robotic system was tested by navigating the detector to trace the phantom and flat-top table while avoiding collision and maintaining the closest possible proximity to the common volume. The robot base and tool coordinates were used for image reconstruction. Results: The robotic SPECT system was able to maneuver parallel-hole and pinhole collimated SPECT detectors in close proximity to the phantom, minimizing impact of the flat-top couch on detector radius of rotation. Without background, all five spheres were visible in the reconstructed parallel-hole image, while four spheres, all except the smallest one, were visible in the reconstructed pinhole image. With background, three spheres of 17,22, and 28 mm diameters were readily observed with the parallel-hole imaging, and the targeted spheres (22 and 28 mm diameters) were readily observed in the pinhole region-of-interest imaging. Conclusions: Onboard SPECT could be achieved by a robot maneuvering a SPECT detector about patients in position for radiation therapy on a flat-top couch. The robot inherent coordinate frames could be an effective means to estimate detector pose for use in SPECT image reconstruction. [ABSTRACT FROM AUTHOR]

Highlights: [•] A new error model for the calibration of gimbaled IMU is presented. [•] Gyro’s calibration is separated from accelerometers. [•] Parameters observability is analyzed by the theory of relative output sensitivity. [Copyright &y& Elsevier]

We present a system consisting of a miniature unmanned aerial vehicle (UAV) and a small carrier vehicle, in which the UAV is capable of autonomously starting from the moving ground vehicle, tracking it at a constant distance and landing on a platform on the carrier in motion. Our visual tracking approach differs from other methods by using low-cost, lightweight commodity consumer hardware. As main sensor we use a Wii remote infrared (IR) camera, which allows robust tracking of a pattern of IR lights in conditions without direct sunlight. The system does not need to communicate with the ground vehicle and works with an onboard 8-bit microcontroller. Nevertheless the position and orientation relative to the IR pattern is estimated at a frequency of approximately 50 Hz. This enables the UAV to fly fully autonomously, performing flight control, self-stabilisation and visual tracking of the ground vehicle. We present experiments in which our UAV performs autonomous flights with a moving ground carrier describing a circular path and where the carrier is rotating. The system provides small errors and allows for safe, autonomous indoor flights. [ABSTRACT FROM AUTHOR]

To lower vehicle greenhouse gas emissions, many automotive companies are exploring fuel cell technologies, which combine hydrogen and oxygen to produce electricity and water. While hydrogen storage and infrastructure remain issues, Renault and Nuvera Fuel Cells are developing an onboard fuel processor, which can convert a variety of fuels into hydrogen to power these fuel cell vehicles. The fuel processor is now small enough and powerful enough for use on a vehicle. The catalysts and heat exchangers occupy 80l and can be packaged with balance of plant controls components in a 150-l volume designed to fit under the vehicle. Recent systems can operate on gasoline, ethanol, and methanol with fuel inputs up to 200kWth and hydrogen efficiencies above 77%. The startup time is now less than 4min to lower the CO in the hydrogen stream to the target value for the fuel cell. [Copyright &y& Elsevier]

A method for detecting faults in the components of gas turbines, based on the use of non-linear engine models and optimization techniques, is presented. The method determines deviations in mass flow capacity and efficiency of individual engine components through minimization of appropriate cost function, formulated such that measurements are matched in an optimum way. Component performance deviations are expressed through appropriate modification factors, which are used as health parameters. The modification factors are coupled to a non-linear engine performance model and can represent different health conditions of the engine. The problem of fault diagnosis is formulated as the problem of determining the values of these factors from a given set of measurement data. The novel aspect of the method presented in this paper is that it can be used to determine health factors that are less, equal or larger in number than the available performance measurements. When measurements are fewer than the parameters to be determined, solutions are derived using an approach of the maximum likelihood type. It is demonstrated than such a solution can provide successful diagnosis for the majority of fault types expected to occur in an engine. The method presented is substantiated by application to a large bypass ratio, partially mixed, turbofan, typical of the large civil aircraft engine configuration in today's aircrafts. An extensive set of component faults is studied, representing malfunctions expected to occur in practice. The method is shown to perform successfully in fault identification over this set, using a limited number of measurements representative of current onboard instrumentation. [ABSTRACT FROM AUTHOR]

Nanosatellites are being widely used in various missions, including remote sensing applications. However, the difficulty lies in mission operation due to downlink speed limitation in nanosatellites. Considering the global cloud fraction of 67%, retrieving clear images through the limited downlink capacity becomes a larger issue. In order to solve this problem, we propose an image prioritization method based on cloud coverage using CNN. The CNN is designed to be lightweight and to be able to prioritize RGB images for nanosatellite application. As previous CNNs are too heavy for onboard processing, new strategies are introduced to lighten the network. The input size is reduced, and patch decomposition is implemented for reduced memory usage. Replication padding is applied on the first block to suppress border ambiguity in the patches. The depth of the network is reduced for small input size adaptation, and the number of kernels is reduced to decrease the total number of parameters. Lastly, a multi-stream architecture is implemented to suppress the network from optimizing on color features. As a result, the number of parameters was reduced down to 0.4%, and the inference time was reduced down to 4.3% of the original network while maintaining approximately 70% precision. We expect that the proposed method will enhance the downlink capability of clear images in nanosatellites by 112%. [ABSTRACT FROM AUTHOR]