Abstract:Predictive maintenance (PdM) can improve the aviation equipment readiness in minimal cost, and PdM is also one key enabler to agile combat support. Problems and challenges were analyzed from the perspective of maintenance and support practices in this paper. Firstly, three maintenance methods were compared and each of their suitability was discussed. Secondly, organizations, events, and forms involved in PdM were analyzed. Then, problems against implementation of PdM were summarized in terms of reduction of the maintenance workload and improvement of aviation equipment readiness. The effects of the maintenance information system were also evaluated. Challenges were explained from the perspective of personnel resource, repair parts supply, technical and organizational culture. Lastly, some suggestions were proposed to implement the PdM in our aviation equipment maintenance and support.

Abstract:With the development of Global Navigation Satellite System (GNSS), satellite-based positioning technology has become an important data source for aviation navigation. However, in scenarios involving unmanned urban air mobility (UAM) applications, satellite positioning is susceptible to multipath (MP) and non-line-of-sight (NLOS) signals leading to deterioration in positioning accuracy, posing a challenge to aircraft safety. To address this problem, a proposed method utilizes the K-LSTM model for satellite positioning error estimation. Firstly, the K-means clustering method is used to detect MP/NLOS signals. Secondly, investigating the relationship between satellite observations and positioning errors in different environments and extending the network model. This extension involves adding a droupout layer, a ReLU layer, a fully-connected layer, and a regression layer on top of the Long Short-Term Memory (LSTM) neural network. Finally, using the extended LSTM model to estimate and correct the localization error caused by MP/NLOS signals. The experimental results reveal that in the static urban canyon environment, the localization errors of the clustered MP/NLOS signals are 0.6m, 0.9m, and 1.0m in the east, north, and up directions, respectively, after the correction by the extended LSTM model. Additionally, the localization errors in the dynamic reflection environment are 1.5m, 1.0m, and 2.5m in the east, north, and up directions, respectively. These results demonstrate significant enhancements in localization accuracies compared to the pre-correction errors.

Abstract:The variable pitch governor controls the propeller to maintain a constant speed, so that the propeller can be energy-saving and efficient in a wider range of flight envelope; many foreign countries have developed variable pitch governor with electro-hydraulic servo through a number of advanced turboprop aircraft, while China has only few self-developed variable pitch governor products, many of which are mechanical-hydraulic type. This paper introduces the mechanism and background of the governor and reviews its current research status at home and abroad. Besides, the key technical problems such as insufficient lightweight reliability strategy, internal electro-hydraulic servo valve oil sensitivity, and difficulty in the integration of the propulsion system electronic control unit are analyzed for the electro-hydraulic servo type governor. Based on that, the paper also looks forward to the trends of electrification, digitalization, and intelligentization in the technology of variable-pitch governor for turboprop aircraft. The corresponding solution ideas are provided in order to provide reference for the further research of the advanced governor in China.

Abstract:Aircraft flight quality assessment is a critical process for evaluating the training effects and improving the training standards of pilots. Traditional evaluation methods rely heavily on the subjective scoring by flight instructors, which suffer from subjectivity and limited accuracy. To enhance the objectivity and precision of flight quality assessment, this paper introduces a novel evaluation method that integrates Grey Correlation Analysis (GCA) with the XGBoost algorithm. GCA is utilized to identify flight parameters closely related to flight quality, while the XGBoost algorithm is employed to construct a flight quality assessment model. The high accuracy of the proposed method is verified through the evaluation of actual flight training data. The study demonstrates that the method can effectively enhance the scientific and precise nature of flight quality assessment, providing robust technical support for pilot training.

Abstract:Airline maintainable parts of whole aircraft are one of the important products in forward maintenance design of civil aircraft. The traditional determination method is based on the composition of existing aircraft finished parts, strongly relying on the technical resources and support provided by suppliers. It cannot consider the needs of maintenance design at the beginning of product design, carry out independent forward maintenance design, and establish an economic comprehensive indicator system for monitoring and feedback. It cannot apply and practice direct maintenance cost analysis and control for civil aircraft throughout the entire life cycle, resulting in the final determined airline maintainable parts not meeting the needs of customers for replacement and maintenance and reducing maintenance costs. Based on the above shortcomings, this paper proposes a method for identifying and classifying airline maintainable parts of whole aircraft based on forward maintenance design, establishes the process of forward maintenance design of this method,analyzes the qualitative discrimination logic of this method,and determines the quantitative tradeoff index DMC of this method and establishes the engineering model for calculating the index.Finally,the method can be applied to the classification and tradeoff of airline maintainable parts through a numerical example.The results show that this research method establishes the maintenance forward design process for maintainable parts of the whole aircraft, can weigh and decide airline maintainable parts and classification of the whole aircraft, and can carry out maintenance activity design and economic index monitoring based on the maintainable parts of the whole aircraft. At the same time,it can iteratively update the redesign of airline maintainable parts and provide references for the redesign of airline maintainable parts.

Abstract:With the gradual unmanned, intelligent, and clustered development of aircraft, the air battlefield is gradually entering the era of intelligent air combat. Major aviation powers such as the United States and China, as well as related research institutions, are also focusing on exploration and research of key technologies for intelligent air combat. Deep reinforcement learning combines the perceptual ability of deep learning with the decision-making ability of reinforcement learning, demonstrating significant advantages in the emergence of air combat capabilities. This article, based on the urgent needs of intelligent air combat development, analyzes and summarizes the mainstream algorithms in the field of deep reinforcement learning, and explores the points of integration with the air combat field. From the perspective of algorithm implementation, it identifies key technologies of deep reinforcement learning in air combat. By sorting out the current cutting-edge technological achievements in the field of air combat, it is concluded that the future research on deep reinforcement learning will develop from single-to-single air combat to cluster air combat. Finally, the challenges algorithm faces are proposed, providing reference and guidance for the development of intelligent algorithms in intelligent air combat.

Abstract:To accomplish the task of searching for specific indoor targets with a drone, even when system power consumption and platform weight are constrained, a low-cost, low-power, small-size drone design for autonomous indoor target search is proposed. Firstly, a suitable UAV hardware architecture based on constraints is chosen, and the controller is designed using saturation control. Besides, a simple sensor combination comprising three TF-Luna laser sensors is employed to gather environmental information. In the obstacle avoidance algorithm design, the avoidance logic of the Bug algorithm is referenced, achieving the design of the UAV"s autonomous cruising mode. Then, the image acquisition chip is used to obtain real-time image information in the drone"s flight direction. The chip integrated with the YOLO-v2 algorithm detects target information in the images. Furthermore, a central region following strategy is employed to achieve real-time tracking of the target. Finally, the simulation and actual flight of the autonomous cruise and target detection tracking tasks were completed at a speed of 1m/s in a 6m x 6m Simulink simulation environment and real-world scenarios.

Abstract:Compared with conventional fuel aircraft or electric aircraft with a single battery source, the adoption of hybrid power in UAVs has become an increasingly popular research direction because it will reduce carbon emissions, reduce energy consumption or increase flight time.However, due to the complex operating conditions and drastic load changes of UAV, the power demand cannot be satisfied by fuel cell alone. It is necessary to add energy storage elements such as lithium battery or super capacitor as its auxiliary power supply. Therefore, the research on energy management strategy of hybrid power system with fuel cell as the main power supply is of great significance to solve the problem of UAV endurance time. Focusing on the UAV hybrid system based on fuel cell-lithium battery-supercapacitor, a model predictive control energy management strategy based on the minimum equivalent hydrogen consumption algorithm is proposed in this paper. The strategy applies the minimum equivalent hydrogen consumption strategy to the model predictive control framework, which not only meets the system load demand, but also improves the fuel economy. Finally, the simulation results show that the hydrogen consumption of the system is reduced effectively and the optimal power distribution is realized.

Abstract:In order to improve the take-off and landing performance of civil transport aircraft, it is necessary to control the flow separation on the suction surface of the wing. The vortex generator is a simple passive flow control technology that has potential positive benefits for delaying the separation of the fluid boundary layer and improving the take-off and landing performance of the aircraft. Research on rectangular vortex generators was carried out through civil transport aircraft model wind tunnel tests. The rectangular vortex generator was installed near the leading edge of the inner wing of the wing. The test used smoke flow technology, fluorescent tuft technology and PIV particle image velocity measurement technology. Through smoke flow experiments and fluorescent tuft experiments, the conclusion that rectangular vortex generators can improve the separation of the inner wing downstream area of the wing was qualitatively captured; Through the PIV particle image velocimetry experiment, we quantitatively obtained a pattern of the use of a rectangular vortex generator at a designated station downstream of the inner wing of the wing, which can force the separation flow in the separation area to become an airfoil-attached flow again. Based on the test results, the rectangular vortex generator can significantly improve the low-speed characteristics of civil aircraft.

Abstract:The new GH4198 nickel based superalloy is a key material for high-performance aviation engine hot end components, and its turning workability has a significant impact on surface quality and service performance. Conduct turning experiments based on single factor method and study the influence of turning parameters on turning force, turning temperature, and surface roughness. The experimental results show that within the range of experimental parameters, both turning force and turning temperature increase continuously with the increase of turning parameters. Among them, the factor that has the greatest impact on turning force is turning depth, with a maximum turning force of 685.2N; The factor that has the greatest impact on turning temperature is turning speed, with a maximum turning temperature of 484.8 ℃; The feed rate has the greatest impact on surface roughness, with a minimum surface roughness of 0.346 μm. Therefore, during rough machining, a turning speed of v=130m/min, a feed rate of f=0.14mm/r, and a turning depth of ap=0.8mm can be selected to achieve efficient material removal. During precision machining, a turning speed of v=90m/min, a feed rate of f=0.06mm/r, and a turning depth of ap=0.3mm can be selected to improve surface quality, providing a theoretical basis for the processing of the new material GH4198.