Artificial Neural Network Based Mission Planning Mechanism for Spacecraft

Li, Zhaoyu,Xu, Rui,Cui, Pingyuan,Zhu, Shengying The Korean Society for Aeronautical Space Sciences 2018 International Journal of Aeronautical and Space Sc Vol.19 No.1

The ability to plan and react fast in dynamic space environments is central to intelligent behavior of spacecraft. For space and robotic applications, many planners have been used. But it is difficult to encode the domain knowledge and directly use existing techniques such as heuristic to improve the performance of the application systems. Therefore, regarding planning as an advanced control problem, this paper first proposes an autonomous mission planning and action selection mechanism through a multiple layer perceptron neural network approach to select actions in planning process and improve efficiency. To prove the availability and effectiveness, we use autonomous mission planning problems of the spacecraft, which is a sophisticated system with complex subsystems and constraints as an example. Simulation results have shown that artificial neural networks (ANNs) are usable for planning problems. Compared with the existing planning method in EUROPA, the mechanism using ANNs is more efficient and can guarantee stable performance. Therefore, the mechanism proposed in this paper is more suitable for planning problems of spacecraft that require real time and stability.

Correction to: Artificial Neural Network Based Mission Planning Mechanism for Spacecraft

Zhaoyu Li,Rui Xu,Pingyuan Cui,Shengying Zhu 한국항공우주학회 2018 International Journal of Aeronautical and Space Sc Vol.19 No.3

The ability to plan and react fast in dynamic space environments is central to intelligent behavior of spacecraft. For space and robotic applications, many planners have been used. But it is difficult to encode the domain knowledge and directly use existing techniques such as heuristic to improve the performance of the application systems. Therefore, regarding planning as an advanced control problem, this paper first proposes an autonomous mission planning and action selection mechanism through a multiple layer perceptron neural network approach to select actions in planning process and improve efficiency. To prove the availability and effectiveness, we use autonomous mission planning problems of the spacecraft, which is a sophisticated system with complex subsystems and constraints as an example. Simulation results have shown that artificial neural networks (ANNs) are usable for planning problems. Compared with the existing planning method in EUROPA, the mechanism using ANNs is more efficient and can guarantee stable performance. Therefore, the mechanism proposed in this paper is more suitable for planning problems of spacecraft that require real time and stability.

Artificial Neural Networks-Based Mission Planning Mechanism for Spacecraft

Zhaoyu Li,Rui Xu,Pingyuan Cui,Shengying Zhu 한국항공우주학회 2018 International Journal of Aeronautical and Space Sc Vol.19 No.1

The ability to plan and react fast in dynamic space environments is central to intelligent behavior of spacecraft. For space and robotic applications, many planners have been used. But it is difficult to encode the domain knowledge and directly use existing techniques such as heuristic to improve the performance of the application systems. Therefore, regarding planning as an advanced control problem, this paper first proposes an autonomous mission planning and action selection mechanism through a multiple layer perceptron neural network approach to select actions in planning process and improve efficiency. To prove the availability and effectiveness, we use autonomous mission planning problems of the spacecraft, which is a sophisticated system with complex subsystems and constraints as an example. Simulation results have shown that artificial neural networks (ANNs) are usable for planning problems. Compared with the existing planning method in EUROPA, the mechanism using ANNs is more efficient and can guarantee stable performance. Therefore, the mechanism proposed in this paper is more suitable for planning problems of spacecraft that require real time and stability.

Characteristics of the Infection of Tilletia laevis Kühn (syn. Tilletia foetida (Wallr.) Liro.) in Compatible Wheat

Zhaoyu Ren,Wei Zhang,Mengke Wang,Haifeng Gao,Huimin Shen,Chunping Wang,Taiguo Liu,Wanquan Chen,Li Gao 한국식물병리학회 2021 Plant Pathology Journal Vol.37 No.5

Tilletia laevis Kühn (syn. Tilletia foetida (Wallr.) Liro.) causes wheat common bunt, which is one of the most devastating plant diseases in the world. Common bunt can result in a reduction of 80% or even a total loss of wheat production. In this study, the characteristics of T. laevis infection in compatible wheat plants were defined based on the combination of scanning electron mi- croscopy, transmission electron microscopy and laser scanning confocal microscopy. We found T. laevis could lead to the abnormal growth of wheat tissues and cells, such as leakage of chloroplasts, deformities, disordered arrangements of mesophyll cells and also thickening of the cell wall of mesophyll cells in leaf tissue. What’s more, T. laevis teliospores were found in the roots, stems, flag leaves, and glumes of infected wheat plants instead of just in the ovaries, as previously reported. The abnormal characteristics caused by T. laevis may be used for early detection of this pathogen instead of molecular markers in addition to providing theoretical insights into T. laevis and wheat interactions for breed- ing of common bunt resistance.

Field- and thickness-dependent performance of tandem organic light-emitting diodes with buffer-modified fullerene/copper phthalocyanine heterojunction as interconnector

Zhaoyue Lü,Xiong Li,Yue Wang,Jing Xiao,Penglai Xu 한국물리학회 2014 Current Applied Physics Vol.14 No.11

Tandem organic light-emitting diodes (OLEDs) with the buffer-modified fullerene/copper phthalocyanine (LiF/C60/CuPc/MoO3) as interconnector have been investigated. The properties of tandem OLEDs are dependent on electric field, which is induced by electric-field-dependence of charge generation (by electric filed and photons) and separation in such an interconnector structure. At low electric field, because of less generated-charges and light-absorption of C60/CuPc film, current efficiency and brightness of tandem OLEDs with two emissive units exhibit less than twice higher than those of conventional single-unit device. But more than twofold enhancement of current efficiency and brightness is observed at higher electric field due to a large number of charges generated in the interconnector. Meanwhile, the performance of tandem devices is affected by the thickness of C60 and CuPc. The optimal thickness is related to their exciton diffusion length.

Partition-based 3 + 2-axis tool path generation for freeform surface machining using a non-spherical tool

Hao Jiancheng,Li Zhaoyu,Li Xiangyu,Xie Fubao,He Dong,Tang Kai 한국CDE학회 2022 Journal of computational design and engineering Vol.9 No.5

When machining a complex freeform part, using a non-spherical tool could significantly improve the machining efficiency, as one can adaptively adjust the tool posture to maximize its contact area with the part surface. However, since adjusting the tool posture requires changing the tool orientation, a five-axis machine tool is needed, which is extremely expensive as compared to a conventional three-axis machine tool. Moreover, for a complex freeform surface with high curvature variation, to match its curvature change, the tool axis has to drastically change accordingly, thus inducing high velocity and acceleration on the machine tool’s rotary axes. To address these issues, in this paper we propose a partition-based 3 + 2-axis strategy for machining a general complex freeform surface with a non-spherical tool. As only a finite small number of distinct tool orientations are needed for 3 + 2-axis machining, an indexed three-axis machine tool suffices, thus relieving the need of an expensive five-axis machine tool. In addition, the much-increased rigidity of the three linear axes of the machine tool will greatly improve the kinematics and dynamics of the machine tool and thus enhance the machining accuracy. Experiments in both computer simulation and physical machining are carried out, whose results confirm that, when compared to using a conventional spherical cutter, by using a non-spherical cutter and adaptively adjusting the contacting tool posture and the feed direction, significant improvement in machining efficiency could be achieved, e.g., more than 50% achieved in our experiments.

Determination and prediction of the digestible and metabolizable energy contents of corn germ meal in growing pigs

Meng Shi,Zhaoyu Liu,Hong Liang Wang,Chuanxin Shi,Ling Liu,Junjun Wang,Defa Li,Shuai Zhang 아세아·태평양축산학회 2019 Animal Bioscience Vol.32 No.3

Objective: This experiment was conducted to determine the chemical composition, digestible energy (DE) and metabolizable energy (ME) contents of corn germ meals (CGM) and to develop equations to predict the corresponding energy contents based on the chemical characteristics of individual CGM. Methods: Sixty-six barrows (initial body weight = 51.3±4.6 kg) were allotted to 11 diets including a basal diet and 10 CGM test diets in a completely randomized design. In the test diets, CGM was included in replacement of 30% of the energy-providing ingredients in the basal diet, resulting in a final inclusion rate of 29.1%. Each diet was fed to 6 barrows housed in individual metabolism crates for a 7-d acclimation period followed by a 5-d total but separate collection of feces and urine. Results: Considerable variation was observed in acid-hydrolyzed ether extract, ether extract, ash, calcium (Ca) and total phosphorus contents among the CGM samples. On dry matter (DM) basis, the DE and ME contents of the CGM ranged from 10.22 to 15.83 MJ/kg and from 9.94 to 15.43 MJ/kg, respectively. The acid detergent fiber (ADF) contents were negatively correlated with the DE and ME contents of CGM samples. The best-fit prediction equations for the DE and ME values (MJ/kg DM) of the 10 CGM were: DE = 26.85–0.28 insoluble dietary fiber (%)–17.79 Ca (%); ME = 21.05–0.43 ADF (%)–11.40 Ca (%). Conclusion: The chemical compositions of CGM vary depending on sources, particularly in ether extract and Ca. The DE and ME values of CGM can be predicted based on their chemical composition in growing pigs.

MMC‑modified sub‑module structure with double reverse blocking IGBTs

Yiqi Liu,Zhaoyu Duan,Qichao Chen,Bingkun Li,Mingfei Ban,Zhenjie Li 전력전자학회 2023 JOURNAL OF POWER ELECTRONICS Vol.23 No.3

In high-voltage direct current (HVDC) systems, among the voltage source converters (VSCs), the modular multilevel converter (MMC) is a popular choice for power transmission. Unfortunately, the conventional half-bridge sub-module (SM) cannot deal with DC faults by itself. Thus, improved SM topologies enabling DC fault ride-through are significant. With this in mind, an MMC-modified SM structure is presented with double reverse blocking IGBTs (DRBSM). When all of the IGBTs in an MMC are blocked, the DRBSM can insert two capacitors in series to the fault circuit to rapidly overcome the DC fault. First, the DRBSM topology and working principle are analyzed. Second, the DRBSM control strategy is illustrated. Third, the device withstand voltage, DC fault ride-through, cost, and loss performance of the DRBSM are presented in detail. Finally, according to simulation results, the DRBSM fault ride-through speed is shown to be as fast as the full-bridge SM, and faster than the clamp double SM. In addition, experimental results validate the feasibility of the proposed DRBSM structure.

Hybrid DC circuit breaker with reduced fault isolation time and current limiting capability

Qichao Chen,Bingkun Li,Laicheng Yin,Junyuan Zheng,Zhaoyu Duan,Yiqi Liu 전력전자학회 2024 JOURNAL OF POWER ELECTRONICS Vol.24 No.1

DC circuit breakers (DCCBs) are key pieces of equipment to ensure the safe and stable operation of DC grids. However, current DCCB schemes generally have problems such as a slow fault clearing speed and a poor current limiting effect. This paper proposes a current-limited hybrid DC circuit breaker (CLHCB) that limits fault current and has fast fault isolation, which reduces the capacity requirements. The current limiting inductor in the fault current limiter (FCL) provides the current limiting capability. In addition, the energy dissipation circuit (EDC) is in parallel to reduce the energy dissipation in metal oxide arresters (MOAs) and to decrease the fault isolation time (FIT), which can reduce the thermal effects of MOAs and improve their reliability. Simulation results verify the working principle and advantages of the proposed CLHCB. When compared to an ABB HCB under the same simulation parameters, the CLHCB enables fault current limiting and faster fault isolation. Finally, experiments have verified the effectiveness of the proposed CLHCB.

Hybrid DC circuit breaker with current‑limiting capability

Yiqi Liu,Bingkun Li,Laicheng Yin,Junyuan Zheng,Zhaoyu Duan,Zhenjie Li 전력전자학회 2023 JOURNAL OF POWER ELECTRONICS Vol.23 No.4

Nowadays, traditional DC circuit breakers (DCCBs) are always expensive and lack current-limiting capabilities. Hence, this paper proposes a current limiting and low-cost hybrid DC circuit breaker (HCB). When a fault occurs, the paralleled inductors in the proposed HCB are converted to a series connection due to the cutoff of the converter module, effectively limiting the increase of fault current. Then the cascaded IGBTs undertake the transient interruption voltage. Energy dissipation circuits (EDCs) reduce the fault isolation time (FIT) by bypassing the current-limiting inductor during energy dissipation based on the metal oxide varistors (MOVs). Therefore, the proposed HCB can limit the rate of the fault current increase, reducing the FIT and cost. Finally, the feasibility of the proposed HCB is verified by a single-ended equivalent system and DC grid test systems built in PSCAD/EMTDC. In addition, the proposed HCB FIT is 33.7% quicker, its energy consumption is 87%, and its cost is lower than that of the traditional ABB HCB.