Individual tree counting (ITC) is a popular topic in the remote sensing application field. The number and planting density of trees are significant for estimating the yield and for futher planing, etc. Although existing studies have already achieved great performance on tree detection with satellite imagery, the quality is often negatively affected by clouds and heavy fog, which limits the application of high-frequency inventory. Nowadays, with ultra high spatial resolution and convenient usage, Unmanned Aerial Vehicles (UAVs) have become promising tools for obtaining statistics from plantations. However, for large scale areas, a UAV cannot capture the whole region of interest in one photo session. In this paper, a real-time orthophoto mosaicing-based tree counting framework is proposed to detect trees using sequential aerial images, which is very effective for fast detection of large areas. Firstly, to guarantee the speed and accuracy, a multi-planar assumption constrained graph optimization algorithm is proposed to estimate the camera pose and generate orthophoto mosaicing simultaneously. Secondly, to avoid time-consuming box or mask annotations, a point supervised method is designed for tree counting task, which greatly speeds up the entire workflow. We demonstrate the effectiveness of our method by performing extensive experiments on oil-palm and acacia trees. To avoid the delay between data acquisition and processing, the proposed framework algorithm is embedded into the UAV for completing tree counting tasks, which also reduces the quantity of data transmission from the UAV system to the ground station. We evaluate the proposed pipeline using sequential UAV images captured in Indonesia. The proposed pipeline achieves an F1-score of 98.2% for acacia tree detection and 96.3% for oil-palm tree detection with online orthophoto mosaicing generation.

Prognostic and health management (PHM) techniques for power MOSFETs are getting increasing attention recently. A variety of methods have been developed and implemented to conduct lifetime predictions for power MOSFETs. Nevertheless, most of the current studies seem to have limitations in a comprehensive understanding of the nonlinear dynamical degradation process. Single parameter-oriented prediction methods may ignore deeper dynamical behaviors during the degradation. Besides, the methods are incapable of tackling abnormal degradation paths such as a sudden rise. In view of the limitations, a data-driven prediction method taking into consideration the nonlinear dynamical behaviors is developed. To analyze nonlinear and chaotic properties, phase space reconstruction (PSR) is conducted on the time series degradation data. Then, the largest Lyapunov exponent and power spectrum are calculated against aging time. The evolution of nonlinear and chaotic behaviors during the degradation is investigated. Thereby, a novel health indicator (HI) taking into account nonlinear indices is constructed. Subsequently, a prediction method based on a long short-term memory (LSTM) network is proposed. The developed method is validated by an actual degradation dataset. The results show that the developed method is capable of addressing the limitations with desirable accuracies.

This article proposes a novel hybrid health monitoring approach to monitor the system-level degradation of aircraft flight control systems (FCSs). The idea derives from observing the nonlinear hysteresis phenomenon in FCS. First, a health FCS model is developed to implement the nonlinear degradation signal extraction of FCS by building an adaptive-network-based fuzzy inference system, a data-driven method. Subsequently, the jump Markov autoregressive exogenous (JMARX) system with time delays is adopted to establish the FCS system-level degradation model. An expectation maximum-convex optimization algorithm is innovatively proposed to identify the model parameters. After that, three health indicators associated with the degradation model parameters are utilized for FCS system-level health monitoring. Finally, a practical flight experiment is conducted by a civil aircraft. The obtained experimental data is used to validate the effectiveness of the proposed FCS monitoring approach. The model of the time-delay JMARX system gets good modeling evaluation results on mean absolute error, standard deviation, etc. Besides, each of the three health indicators shows a clear FCS degradation tendency, which indicates that the proposed method successfully extracts the degradation information and monitors the health states of FCS. This approach is potential for practical and effective engineering applications in the aviation industry.

Integrated modular avionics is one of the most advanced systems which has been widely applied in modern aircraft. The performance of integrated modular avionics deeply impacts flight mission. Remaining useful life prediction is the critical manner which can efficiently improve the safety and reliability of aircraft. Since integrated modular avionics is a real-time system, the prediction algorithm should have fast learning speed to satisfy the real-time requirement. In this paper, an enhanced online sequential method is proposed to predict the remaining useful life of integrated modular avionics. Firstly, this paper proposes an online sequential network which is based on the architecture of parallel layer network. Secondly, to enhance the learning capability, this paper adopts the extreme learning machine denosing autoencoder to determine the input weights of the network. Thirdly, an adaptive forgetting factor is added to further improve the performance of the proposed method. The effectiveness and the superiority of the proposed method are verified in comparison with three online sequential algorithms on the standard datasets. Finally, a degradation model is built to depict the deteriorated process of integrated modular avionics. The prediction results confirms that the proposed method can effectively address remaining useful life of integrated modular avionics.

In recent years, digital twin technology has attracted more and more attention from experts and scholars. At present, the application of digital twins mainly focuses on the section assembly and equipment installation of the aviation department, but the practice of digital twins for aircraft signals, internal mechanisms, process flow, and so on is less and more difficult. In addition, for the power distribution system of civil aircraft, real-time monitoring of fault detection and health management and other technical means still have great space for development. Real-time acquisition of power distribution system data of assembly lines and its data during flight is a problem waiting to be solved in the aviation industry. Based on this, this paper takes the power distribution system of a certain type of civil aircraft as an example to accomplish the research on the digital twin technology of the power distribution system of civil aircraft, realizing the information, intelligent, and dynamic scene monitoring of the power distribution network of the plane.

Airworthiness regulation documents are critical, which contain massive safe constraints for system design and airworthiness certification. The textual information of airworthiness regulations is organized and stored in a hierarchical and scattered form due to the unique provision structure. The linguistic form of legal provision brings the problems of incompleteness semantic information and syntactic structure to each legal clause, which limits the application of Natural Language Processing (NLP) technology in the field of airworthiness safety. In this article, a novel theory of semantic cohesion is proposed for Chinese airworthiness regulations, in which four critical elements are contained, including definition, model, theorem and rules. The definition of attributive directed graph model is proposed to achieve the graphical representation of airworthiness regulation texts. Moreover, the graphical issue of regulation texts is proved in accordance with the characteristic of hierarchical provision structure based on graph theory, and the rules of edge structure construction are provided. Based on the theory, a new node content link algorithm is proposed to achieve the tasks of semantic cohesion and structure conversion for Chinese airworthiness regulation texts. According to the hierarchical structure characteristic of regulation texts, the algorithm can convert the provision structure to the general narrative linguistic form by constructing edges with semantic cohesion relation. As a result, provision sentences with complete semantic information and syntactic structure can be generated. The algorithm has been deployed on the current 119 airworthiness regulation texts to verify the validity and feasibility. The experimental results show that the algorithm achieves efficient performance in the tasks of structure conversion and semantic cohesion, and the algorithm performs reliably with an accuracy rate of 100%. The problem of application limitation for NLP technology to Chinese airworthiness regulation texts has been resolved, which promotes the intelligent and automatic development of airworthiness safety.