First, two fault tolerant planning algorithms with avoidance of joint static torque limit or joint dynamic torque limit are proposed respectively. The former is suitable for the low-speed manipulators, and the latter ...First, two fault tolerant planning algorithms with avoidance of joint static torque limit or joint dynamic torque limit are proposed respectively. The former is suitable for the low-speed manipulators, and the latter is suitable for the high-speed manipulators. These algorithms not only can insure manipulation tasks to lie within the fault tolerant workspace but also can avoid joint torque limit, and hence can insure a redundant manipulator to be. fault tolerant in both kinematical sense and dynamic sense. Then, the simulation examples for a planar 3R manipulator demonstrate the validity of these algorithms.展开更多
为提升电网故障处置预案匹配效率和准确率,提出了基于语义增强的电网故障处置预案匹配方法。首先,通过微调基于变换器双向编码器表征(bidirectional encoder representations from transformers,BERT)模型的超参数,将故障处置预案中多...为提升电网故障处置预案匹配效率和准确率,提出了基于语义增强的电网故障处置预案匹配方法。首先,通过微调基于变换器双向编码器表征(bidirectional encoder representations from transformers,BERT)模型的超参数,将故障处置预案中多调度对象实体表征为可计算词向量,并接入条件随机场(conditional random field,CRF)模型识别调度对象实体类别;然后,基于残差向量-字词嵌入向量-编码向量(residual vector-embedding vector-encoded vector,RE2)计算电网故障信息和调度对象的语义距离,建立基于BERTCRF-RE2的电网故障处置预案匹配模型;最后,通过某地区电网数据进行验证。结果表明,所提模型有效解决了预案匹配准确率低的问题。展开更多
基金Supported by Beijing Municipal Natural Science Foundation Committee and the High Technology Research and Development Programme of China （No.2003AA404140）.
文摘First, two fault tolerant planning algorithms with avoidance of joint static torque limit or joint dynamic torque limit are proposed respectively. The former is suitable for the low-speed manipulators, and the latter is suitable for the high-speed manipulators. These algorithms not only can insure manipulation tasks to lie within the fault tolerant workspace but also can avoid joint torque limit, and hence can insure a redundant manipulator to be. fault tolerant in both kinematical sense and dynamic sense. Then, the simulation examples for a planar 3R manipulator demonstrate the validity of these algorithms.
文摘为提升电网故障处置预案匹配效率和准确率,提出了基于语义增强的电网故障处置预案匹配方法。首先,通过微调基于变换器双向编码器表征(bidirectional encoder representations from transformers,BERT)模型的超参数,将故障处置预案中多调度对象实体表征为可计算词向量,并接入条件随机场(conditional random field,CRF)模型识别调度对象实体类别;然后,基于残差向量-字词嵌入向量-编码向量(residual vector-embedding vector-encoded vector,RE2)计算电网故障信息和调度对象的语义距离,建立基于BERTCRF-RE2的电网故障处置预案匹配模型;最后,通过某地区电网数据进行验证。结果表明,所提模型有效解决了预案匹配准确率低的问题。
