摘要：SRAM(static random access memory)-based FPGA(field programmable gate array), owing to its large capacity, high performance, and dynamical reconfiguration, has become an attractive platform for So PC(system on programmable chip) development. However, as the configuration memory and logic memory of the SRAM-based FPGA are highly susceptible to SEUs(single-event upsets) in deep space, it is a challenge to design and implement a highly reliable FPGA-based system for spacecraft, and no practical architecture has been proposed. In this paper, a new architecture for a reliable and reconfigurable FPGAbased computer in a highly critical GNC(guidance navigation and control) system is proposed. To mitigate the effect of an SEU on the system, multi-layer reconfiguration and multi-layer TMR(triple module redundancy) techniques are proposed, with a reliable reconfigurable real-time operating system(Space OS) managing the system level fault tolerance of the computer in the architecture. The proposed architecture for the reconfigurable FPGA-based computer has been implemented with COTS(commercial off the shelf) FPGA and has firstly been applied to the GNC system of a circumlunar return and reentry flight vehicle. The in-orbit results show that the proposed architecture is capable of meeting the requirements of high reliability and high availability, and can provide the expressive varying functionality and runtime flexibility for an FPGA-based GNC computer in deep space.

摘要：With the explosion of information nowadays, applying data storage safety requirements has become a new challenge, especially in high data available cluster environments. With the emergence of Storage Area Networks （SANs）, storage can be network-based and consolidated, and mass data movements via Fiber Channels （FCs） can be of very high speed. Based on these features, this paper introduces a dual-node storage cluster designed for remote mirroring as a concurrent data replication method to protect data during system failures. This design takes full advantage of a SAN system＇s benefits, and it adopts a synchronous protocol to guarantee a fully up-to-date data copy on the remote site. By developing a Linux kernel module to control the I/O flow and by using the technologies of software Logic Unit Number （LUN） masking, background online resynchronization and a self-management daemon, we have achieved a reliable mirroring system with the characteristics of server-free data replication, fault tolerance, online disaster recovery and high performance. In this study, we implemented the design in a remote mirror subsystem built on a software Fiber Channel Storage Area Network （FC-SAN） system.

摘要：This paper focuses on solving a problem of improving system robustness and the efficiency of a distributed system at the same time. fault tolerance with active replication and load balancing techniques are used. The pros and cons of both techniques are analyzed, and a novel load balancing framework for fault tolerant systems with active replication is presented. Hierarchical architecture is described in detail. The framework can dynamically adjust fault tolerant groups and their memberships with respect to system loads. Three potential task scheduler group selection methods are proposed and simulation tests are made. Further analysis of test data is done and helpful observations for system design are also pointed out, including effects of task arrival intensity and task set size, relationship between total task execution time and single task execution time.

摘要：The use of robotic manipulators in remote and sensitive areas calls for more robust solutions when handling joint failure, and the industry demands mathematically robust approaches to handle even the worst case scenarios. For both serial and parallel manipulators torque failure is indeed a worst case scenario. Thus, a systematic analysis of the effects of external forces on manipulators with passive joints is presented. For serial manipulators we find under what conditions the robot is conditionally equilibrated, that is, equilibrated with respect to a specific external force. These conditions are, as expected, very restrictive. The serial, or subchain, case serves as a good platform for analyzing parallel manipulators. In parallel manipulators passive joints can appear as a design choice or as a result of torque failure. In both cases a good understanding of the effects that passive joints have on the mobility and motion of the parallel manipulator is crucial. We first look at the effects that passive joints have on the mobility of the mechanism. Then, if the mobility considering passive joints only is not zero we find a condition similar to the serial case for which the parallel manipulator is conditionally equilibrated with respect to a specific external force.

摘要：The control method of highly redundant robot manipulators is introduced. A decentralized autonomous control scheme is used to guide the movement of robot manipulators so that the work done by manipulators is minimized. The method of computing pseudoinverse which needs too many complicated calculation can be avoided. Then the calculation and control of robots are simplified. At the same time system robustness/fault tolerance is achieved.