In view of the characteristics of warehouse or freight yard carrying out transfer and loading conditions,the performance parameter matching of the power system of an electric transfer vehicle was studied,and the drivi...In view of the characteristics of warehouse or freight yard carrying out transfer and loading conditions,the performance parameter matching of the power system of an electric transfer vehicle was studied,and the driving motor and power battery of the key components of the vehicle were reasonably selected.Cruise software was used to simulate the loading process of the vehicle.The results show that the performance design of the power system of the electric transport vehicle and its key components is reasonable,meeting the requirements of maximum speed,climbing performance and starting driving performance,and providing a reference and credible basis for the design of the power system of the vehicle.展开更多
传统推荐算法多基于用户兴趣的静态属性获得用户偏好,忽略了用户兴趣漂移问题,为此,提出了解决该问题的融合用户兴趣漂移的Top-N推荐算法。利用长短期记忆网络(LSTM,long short term memory)处理时序数据的优势表示用户短期兴趣漂移规律...传统推荐算法多基于用户兴趣的静态属性获得用户偏好,忽略了用户兴趣漂移问题,为此,提出了解决该问题的融合用户兴趣漂移的Top-N推荐算法。利用长短期记忆网络(LSTM,long short term memory)处理时序数据的优势表示用户短期兴趣漂移规律,用矩阵分解得到的固定向量表示用户的长期兴趣,将注意力机制纳入LSTM隐藏状态的表示中来获取用户长短期兴趣关联。实验结果表明,所提算法与当前流行算法相比,在Top-N项目推荐中具有更优性能。展开更多
文摘In view of the characteristics of warehouse or freight yard carrying out transfer and loading conditions,the performance parameter matching of the power system of an electric transfer vehicle was studied,and the driving motor and power battery of the key components of the vehicle were reasonably selected.Cruise software was used to simulate the loading process of the vehicle.The results show that the performance design of the power system of the electric transport vehicle and its key components is reasonable,meeting the requirements of maximum speed,climbing performance and starting driving performance,and providing a reference and credible basis for the design of the power system of the vehicle.
文摘传统推荐算法多基于用户兴趣的静态属性获得用户偏好,忽略了用户兴趣漂移问题,为此,提出了解决该问题的融合用户兴趣漂移的Top-N推荐算法。利用长短期记忆网络(LSTM,long short term memory)处理时序数据的优势表示用户短期兴趣漂移规律,用矩阵分解得到的固定向量表示用户的长期兴趣,将注意力机制纳入LSTM隐藏状态的表示中来获取用户长短期兴趣关联。实验结果表明,所提算法与当前流行算法相比,在Top-N项目推荐中具有更优性能。