Pub Date : 2023-06-23DOI: 10.1109/ISAS59543.2023.10164429
Hongyu Qu, Tian-Yu Ren
In this paper, based on the principle of attachment coordinate system and Maneuvering Modeling Group modeling principle, the motion model is constructed. The fuzzy PID control algorithm is used to design the heading controller and the track point tracking algorithm. The motion model is simulated and designed to realize the track point tracking. The method of fuzzy inference is used to overcome the shortcomings of the traditional PID control that cannot modify the PID parameters online. At the same time, pre-processing of point cloud data and LIDAR-based obstacle detection are realized. Experimental results verify the accuracy of model design and the effectiveness of autonomous navigation control design.
{"title":"Autonomous Unmanned Surface Vessel Based on GPS And Radar","authors":"Hongyu Qu, Tian-Yu Ren","doi":"10.1109/ISAS59543.2023.10164429","DOIUrl":"https://doi.org/10.1109/ISAS59543.2023.10164429","url":null,"abstract":"In this paper, based on the principle of attachment coordinate system and Maneuvering Modeling Group modeling principle, the motion model is constructed. The fuzzy PID control algorithm is used to design the heading controller and the track point tracking algorithm. The motion model is simulated and designed to realize the track point tracking. The method of fuzzy inference is used to overcome the shortcomings of the traditional PID control that cannot modify the PID parameters online. At the same time, pre-processing of point cloud data and LIDAR-based obstacle detection are realized. Experimental results verify the accuracy of model design and the effectiveness of autonomous navigation control design.","PeriodicalId":199115,"journal":{"name":"2023 6th International Symposium on Autonomous Systems (ISAS)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125238967","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-23DOI: 10.1109/ISAS59543.2023.10164379
Jiaao Yang, Fuyang Chen
In this paper, a nonlinear control scheme is proposed for the altitude tracking of morphing aircraft with unknown aerodynamic disturbances under the condition of high maneuver. Considering the characteristics of high order and strong nonlinearity of the system, the scheme divides the system into inner loop (pitch angle tracking) and outer loop (height tracking). An adaptive sliding mode controller is designed for the inner loop subsystem to avoid the influence of unknown aerodynamic disturbances on tracking performance. The upper bound of disturbances is estimated in real time by adaptive update rules to compensate for the unknown disturbances. To prevent the problem of ‘differential explosion’ induced by the high order, a backstepping tracking controller with dynamic surface is designed for the outer loop subsystem. The stability of the closed-loop system is analyzed utilizing Lyapunov theory. Finally, the effectiveness of the proposed scheme is validated by comparative simulations.
{"title":"Adaptive Backstepping Sliding Mode Control of Morphing Aircraft with Unknown Disturbances","authors":"Jiaao Yang, Fuyang Chen","doi":"10.1109/ISAS59543.2023.10164379","DOIUrl":"https://doi.org/10.1109/ISAS59543.2023.10164379","url":null,"abstract":"In this paper, a nonlinear control scheme is proposed for the altitude tracking of morphing aircraft with unknown aerodynamic disturbances under the condition of high maneuver. Considering the characteristics of high order and strong nonlinearity of the system, the scheme divides the system into inner loop (pitch angle tracking) and outer loop (height tracking). An adaptive sliding mode controller is designed for the inner loop subsystem to avoid the influence of unknown aerodynamic disturbances on tracking performance. The upper bound of disturbances is estimated in real time by adaptive update rules to compensate for the unknown disturbances. To prevent the problem of ‘differential explosion’ induced by the high order, a backstepping tracking controller with dynamic surface is designed for the outer loop subsystem. The stability of the closed-loop system is analyzed utilizing Lyapunov theory. Finally, the effectiveness of the proposed scheme is validated by comparative simulations.","PeriodicalId":199115,"journal":{"name":"2023 6th International Symposium on Autonomous Systems (ISAS)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122490575","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-23DOI: 10.1109/ISAS59543.2023.10164577
Linlin Chen, Jun Zhou
Lately, a matrix-weighted flocking control approach for second-order particle multi-agents is contrived by generalizing the Olfati-Saber flocking strategies, which can produce maneuverable (or time-varying) multi-agent formation with various specifications, such as formation scaling, dimension confining and topology setting. In this paper, the generalized Olfati-Saber flocking algorithms are further equipped with an additional term involving constant/time-varying weighting matrices for orientation and rotation maneuverability in flocking lattices. Technical and algorithmic details about orientating and rotating matrices are defined and examined; in particular, probable rotation deficiency in the suggested approach is discussed carefully as well. dozens of numerical simulations in 2D multi-agent systems are illustrated through choosing the weighting matrices as appropriately.
{"title":"Multi-Agent Flocking Formation with Orientating and Rotating Maneuverability","authors":"Linlin Chen, Jun Zhou","doi":"10.1109/ISAS59543.2023.10164577","DOIUrl":"https://doi.org/10.1109/ISAS59543.2023.10164577","url":null,"abstract":"Lately, a matrix-weighted flocking control approach for second-order particle multi-agents is contrived by generalizing the Olfati-Saber flocking strategies, which can produce maneuverable (or time-varying) multi-agent formation with various specifications, such as formation scaling, dimension confining and topology setting. In this paper, the generalized Olfati-Saber flocking algorithms are further equipped with an additional term involving constant/time-varying weighting matrices for orientation and rotation maneuverability in flocking lattices. Technical and algorithmic details about orientating and rotating matrices are defined and examined; in particular, probable rotation deficiency in the suggested approach is discussed carefully as well. dozens of numerical simulations in 2D multi-agent systems are illustrated through choosing the weighting matrices as appropriately.","PeriodicalId":199115,"journal":{"name":"2023 6th International Symposium on Autonomous Systems (ISAS)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121642434","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-23DOI: 10.1109/ISAS59543.2023.10164574
Yonghao Ma, Kecheng Zhang, B. Jiang, S. Simani, Wanglei Cheng
The tracking issue is studied for nonlinear uncertain fully actuated systems in the presence of the actuator’s potential loss of effectiveness fault and bias fault. In contrast to the existing results, this paper takes uncertainties, including totally unknown system dynamics and actuator faults, into consideration. Neural networks are utilized to approximate the unknown dynamics. The adaptive technique is used to update the networks’ weight vector and estimate the unknown bounds of the actuator efficiency factor and bias fault in order to avoid the detrimental effect brought on by uncertainties. Then, a fault-tolerant control method is given to ensure all system’s signals are bound. Finally, a practical example is considered to demonstrate the validity of the main results.
{"title":"Neural-Network-Based Adaptive Fault-Tolerant Control for Nonlinear Systems: A Fully Actuated System Approach","authors":"Yonghao Ma, Kecheng Zhang, B. Jiang, S. Simani, Wanglei Cheng","doi":"10.1109/ISAS59543.2023.10164574","DOIUrl":"https://doi.org/10.1109/ISAS59543.2023.10164574","url":null,"abstract":"The tracking issue is studied for nonlinear uncertain fully actuated systems in the presence of the actuator’s potential loss of effectiveness fault and bias fault. In contrast to the existing results, this paper takes uncertainties, including totally unknown system dynamics and actuator faults, into consideration. Neural networks are utilized to approximate the unknown dynamics. The adaptive technique is used to update the networks’ weight vector and estimate the unknown bounds of the actuator efficiency factor and bias fault in order to avoid the detrimental effect brought on by uncertainties. Then, a fault-tolerant control method is given to ensure all system’s signals are bound. Finally, a practical example is considered to demonstrate the validity of the main results.","PeriodicalId":199115,"journal":{"name":"2023 6th International Symposium on Autonomous Systems (ISAS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127569345","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The tracking problem of the unmanned surface vehicle system is considered in the paper. First, we propose a sliding mode controller (SMC) with nonsingular terminal method to reject the external disturbance. Then, a disturbance observer (DO) is designed to improve the accuracy of the trajectory tracking. Furthermore, the trajectory tracking of the unmanned surface vehicle is realized, then we use Lyapunov stability method to analyze the stability of the tracking error system. Finally, we use simulation to prove the superiority of the proposed method.
{"title":"Trajectory Tracking of Unmanned Surface Vehicle based on Terminal Sliding Mode","authors":"Yue Xie, Yunfei Dai, Xin Li, Qing Chen, Jiemin Yuan, Zhipeng Lu","doi":"10.1109/ISAS59543.2023.10164311","DOIUrl":"https://doi.org/10.1109/ISAS59543.2023.10164311","url":null,"abstract":"The tracking problem of the unmanned surface vehicle system is considered in the paper. First, we propose a sliding mode controller (SMC) with nonsingular terminal method to reject the external disturbance. Then, a disturbance observer (DO) is designed to improve the accuracy of the trajectory tracking. Furthermore, the trajectory tracking of the unmanned surface vehicle is realized, then we use Lyapunov stability method to analyze the stability of the tracking error system. Finally, we use simulation to prove the superiority of the proposed method.","PeriodicalId":199115,"journal":{"name":"2023 6th International Symposium on Autonomous Systems (ISAS)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127670730","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-23DOI: 10.1109/ISAS59543.2023.10164586
Peng Wang, Bin Du, Xiuhui Peng, Mou Chen
In this paper, we propose a distributed strategy to control and drive multiple UAVs to the target locations under the confined environment with obstacle and agent avoidance. The explicit reference governor (ERG) is a simple and systematic approach that provides constraint handling capabilities to prestabilized systems. When designing the ERG, one of the main challenges is the determination of dynamic safety margin that ensures constraints satisfaction. To do this, the robustness to uncertainty is taken into the margin design and provides the invariance property; the dynamic event-triggering mechanism is applied to the optimization of the threshold in the designed margin subject to concave collision constraints. Numerical simulations are performed to investigate the performance of our proposed methodology.
{"title":"Constrained Control of UAV Swarms Using Event-triggered Distributed Explicit Reference Governor","authors":"Peng Wang, Bin Du, Xiuhui Peng, Mou Chen","doi":"10.1109/ISAS59543.2023.10164586","DOIUrl":"https://doi.org/10.1109/ISAS59543.2023.10164586","url":null,"abstract":"In this paper, we propose a distributed strategy to control and drive multiple UAVs to the target locations under the confined environment with obstacle and agent avoidance. The explicit reference governor (ERG) is a simple and systematic approach that provides constraint handling capabilities to prestabilized systems. When designing the ERG, one of the main challenges is the determination of dynamic safety margin that ensures constraints satisfaction. To do this, the robustness to uncertainty is taken into the margin design and provides the invariance property; the dynamic event-triggering mechanism is applied to the optimization of the threshold in the designed margin subject to concave collision constraints. Numerical simulations are performed to investigate the performance of our proposed methodology.","PeriodicalId":199115,"journal":{"name":"2023 6th International Symposium on Autonomous Systems (ISAS)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132696844","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-23DOI: 10.1109/ISAS59543.2023.10164307
Guoyao Huan, Xinhua Wang, Cong Peng, Shiwang Song
In light of the challenges associated with communication rejection and real-time target detection and three-dimensional perception of visual recognition systems, this paper sets out to investigate the real-time recognition and flight verification of UAV formations utilizing a monocular camera. Visual recognition systems constitute the object of study, while UAV serves as the experimental object. The research firstly focuses on devising visual formation schemes and designing system software and hardware architecture. Subsequently, considering the UAV computing power and real-time performance, a lightweight real-time target detection network is constructed to ensure target recognition speed and accuracy improvement. Relying on real-time target detection combined with ranging function, three-dimensional information of the drone is perceived. Lastly, corresponding data from UAVs is collected to train the algorithm and subsequently verify the efficacy of UAV formation and intrusion. Results indicate that the monocular visual recognition method proposed herein has both real-time detection ability and satisfactory target detection accuracy, which carries immense significance towards the development of UAVs, especially visual formation.
{"title":"Visual recognition method of drone formation based on monocular camera","authors":"Guoyao Huan, Xinhua Wang, Cong Peng, Shiwang Song","doi":"10.1109/ISAS59543.2023.10164307","DOIUrl":"https://doi.org/10.1109/ISAS59543.2023.10164307","url":null,"abstract":"In light of the challenges associated with communication rejection and real-time target detection and three-dimensional perception of visual recognition systems, this paper sets out to investigate the real-time recognition and flight verification of UAV formations utilizing a monocular camera. Visual recognition systems constitute the object of study, while UAV serves as the experimental object. The research firstly focuses on devising visual formation schemes and designing system software and hardware architecture. Subsequently, considering the UAV computing power and real-time performance, a lightweight real-time target detection network is constructed to ensure target recognition speed and accuracy improvement. Relying on real-time target detection combined with ranging function, three-dimensional information of the drone is perceived. Lastly, corresponding data from UAVs is collected to train the algorithm and subsequently verify the efficacy of UAV formation and intrusion. Results indicate that the monocular visual recognition method proposed herein has both real-time detection ability and satisfactory target detection accuracy, which carries immense significance towards the development of UAVs, especially visual formation.","PeriodicalId":199115,"journal":{"name":"2023 6th International Symposium on Autonomous Systems (ISAS)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133745981","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-23DOI: 10.1109/ISAS59543.2023.10164489
Yi Hao, Xintao Huan, Kaitao Miao, Han Hu
Consensus problem has been extensively studied in time synchronization for approaching non-consensus clocks to a common time frame. The non-consensus clocks driven by crystal oscillators, per se, are adequate features for device fingerprinting, however. A reflection of the non-consensus crystal oscillator in radio frequency (RF) is the carrier frequency offset (CFO), which has been put under the spotlight in the recent RF fingerprinting research. In this paper, we first investigate the relationship between crystal oscillator and CFO, with illustrating the application of CFO in achieving RF fingerprinting. We then conduct a review on the existing RF fingerprinting schemes leveraging CFO as a critical feature for identification. We also review the state-of-the-art schemes advocating CFO compensation for fingerprinting. Interestingly, two contradictory viewpoints on CFO both promote the research on RF fingerprinting in terms of such as identification accuracy.
{"title":"Non-Consensus Crystal Oscillators Enhanced Radio Frequency Fingerprinting: State-of-The-Art","authors":"Yi Hao, Xintao Huan, Kaitao Miao, Han Hu","doi":"10.1109/ISAS59543.2023.10164489","DOIUrl":"https://doi.org/10.1109/ISAS59543.2023.10164489","url":null,"abstract":"Consensus problem has been extensively studied in time synchronization for approaching non-consensus clocks to a common time frame. The non-consensus clocks driven by crystal oscillators, per se, are adequate features for device fingerprinting, however. A reflection of the non-consensus crystal oscillator in radio frequency (RF) is the carrier frequency offset (CFO), which has been put under the spotlight in the recent RF fingerprinting research. In this paper, we first investigate the relationship between crystal oscillator and CFO, with illustrating the application of CFO in achieving RF fingerprinting. We then conduct a review on the existing RF fingerprinting schemes leveraging CFO as a critical feature for identification. We also review the state-of-the-art schemes advocating CFO compensation for fingerprinting. Interestingly, two contradictory viewpoints on CFO both promote the research on RF fingerprinting in terms of such as identification accuracy.","PeriodicalId":199115,"journal":{"name":"2023 6th International Symposium on Autonomous Systems (ISAS)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133922361","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-06-23DOI: 10.1109/ISAS59543.2023.10164430
Xinxu Ju, X. Jia, Tian Ji, Wenhui Liu
In the framework of event-triggered control, the question of practical tracking of a sort of nonlinear systems with serious uncertainty is addressed in this work by virtue of adaptive output feedback control scheme. Especially, system nonlinearities not only depend on the unmeasurable states, but also allows the existence of output polynomial function. By combining extended Lyapunov matrix inequalities, non-identification adaptive technology and dynamic scaling transformation technology, this article proposes an adaptive output feedback control scheme within the event triggering control framework to realize global practical tracking control of closed-loop system. Simultaneously, it must be mentioned that the proposed control method includes dual gain: static gain and dynamic gain, where the latter can effectively compensate for severe uncertainty, output polynomial functions, time-varying control coefficients, and errors caused by event triggering mechanism; in addition, so as to reduce the transmission frequency of control signals, the event triggering mechanism on account of fixed threshold strategy is adopted. By means of Barbălat’s lemma and Lyapunov’s stability theorem, one can prove that the designed control strategy insures that the closed-loop system states are bounded under any initial conditions, while the tracking error is driven to a prescribed interval after a limited time. Also, the Zeno behavior is successfully ruled out. Eventually, one illustrative example is put forward to verify the correctness of the presented approach.
{"title":"Event triggering based adaptive tracking of uncertain nonlinear systems with unknown control coefficients","authors":"Xinxu Ju, X. Jia, Tian Ji, Wenhui Liu","doi":"10.1109/ISAS59543.2023.10164430","DOIUrl":"https://doi.org/10.1109/ISAS59543.2023.10164430","url":null,"abstract":"In the framework of event-triggered control, the question of practical tracking of a sort of nonlinear systems with serious uncertainty is addressed in this work by virtue of adaptive output feedback control scheme. Especially, system nonlinearities not only depend on the unmeasurable states, but also allows the existence of output polynomial function. By combining extended Lyapunov matrix inequalities, non-identification adaptive technology and dynamic scaling transformation technology, this article proposes an adaptive output feedback control scheme within the event triggering control framework to realize global practical tracking control of closed-loop system. Simultaneously, it must be mentioned that the proposed control method includes dual gain: static gain and dynamic gain, where the latter can effectively compensate for severe uncertainty, output polynomial functions, time-varying control coefficients, and errors caused by event triggering mechanism; in addition, so as to reduce the transmission frequency of control signals, the event triggering mechanism on account of fixed threshold strategy is adopted. By means of Barbălat’s lemma and Lyapunov’s stability theorem, one can prove that the designed control strategy insures that the closed-loop system states are bounded under any initial conditions, while the tracking error is driven to a prescribed interval after a limited time. Also, the Zeno behavior is successfully ruled out. Eventually, one illustrative example is put forward to verify the correctness of the presented approach.","PeriodicalId":199115,"journal":{"name":"2023 6th International Symposium on Autonomous Systems (ISAS)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132204166","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Fault influence and propagation analysis of flight vehicle systems is an important element of flight vehicle health management and also an important problem to be solved. A fault influence model based on data-driven is established, including a prediction model of flight parameters under fault, a dynamic influence path, and an influence degree model. Based on the historical experimental data, a long and short-term memory neural network (LSTM) model is proposed to predict the time-series data of each flight parameter of the flight vehicle under fault; based on the prediction results, a symbolic directed graph (SDG) is used to describe the fault of the flight vehicle system, and then introduce the concept of a compatible path with time-series characteristics to describe the dynamic propagation process of the fault. The case shows that the method proposed in this paper enables qualitative and quantitative analysis of the fault influence, and can reasonably describe the fault propagation path and influence characteristics.
{"title":"Flight Parameter Prediction and Fault Propagation based on Machine Learning and Symbolic Directed Graph","authors":"Wenzhuo Li, Kun Guo, Yuehua Cheng, Hengsong Hu, Cheng Xu, Ziquan Yu","doi":"10.1109/ISAS59543.2023.10164555","DOIUrl":"https://doi.org/10.1109/ISAS59543.2023.10164555","url":null,"abstract":"Fault influence and propagation analysis of flight vehicle systems is an important element of flight vehicle health management and also an important problem to be solved. A fault influence model based on data-driven is established, including a prediction model of flight parameters under fault, a dynamic influence path, and an influence degree model. Based on the historical experimental data, a long and short-term memory neural network (LSTM) model is proposed to predict the time-series data of each flight parameter of the flight vehicle under fault; based on the prediction results, a symbolic directed graph (SDG) is used to describe the fault of the flight vehicle system, and then introduce the concept of a compatible path with time-series characteristics to describe the dynamic propagation process of the fault. The case shows that the method proposed in this paper enables qualitative and quantitative analysis of the fault influence, and can reasonably describe the fault propagation path and influence characteristics.","PeriodicalId":199115,"journal":{"name":"2023 6th International Symposium on Autonomous Systems (ISAS)","volume":"199 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134277579","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：