With regard to function, the strengths for interference articulation of a roller shaft formed a series system. As the three strength reliabilities conditioned each other, there was a problem for the system reliability...With regard to function, the strengths for interference articulation of a roller shaft formed a series system. As the three strength reliabilities conditioned each other, there was a problem for the system reliability to apportion rationally. In fact, there was a transition from safety to deactivation. The state of structure was fuzziness which was in both safety and non-safety states. Therefore the reliability was a fuzzy event which considered the randomness for some design parameters and the fuzziness for the thresholds between generalized strength safety and deactivation. The mathematical model of fuzzy reliability design for the interference articulation of the roller shaft was presented. Eight design examples were calculated.展开更多
文摘With regard to function, the strengths for interference articulation of a roller shaft formed a series system. As the three strength reliabilities conditioned each other, there was a problem for the system reliability to apportion rationally. In fact, there was a transition from safety to deactivation. The state of structure was fuzziness which was in both safety and non-safety states. Therefore the reliability was a fuzzy event which considered the randomness for some design parameters and the fuzziness for the thresholds between generalized strength safety and deactivation. The mathematical model of fuzzy reliability design for the interference articulation of the roller shaft was presented. Eight design examples were calculated.
文摘玻璃生产线退火窑辊道系统轴承运行状态显著影响玻璃品质和生产效率,实时监测各轴承运行状态对确保退火窑系统的平稳运行具有重要意义,提出结合Inception模块和长短期神经网络(Long Short-term Memory,LSTM)的迁移诊断方法,对退火窑辊道系统中的辊道轴承和通轴轴承运行状态进行监测、诊断。首先,使用集合经验模态分解(Ensemble Empirical Mode Decomposition,EEMD)对轴承信号进行分解和重构降噪,并利用直方均衡化增强重构信号小波时频图的聚集性。然后,针对样本充足的辊道轴承,建立Inception-LSTM网络,提取多尺度特征并学习其中的时间依赖关系,实现状态诊断。再次,针对转速不同且样本量少的通轴轴承,以辊道轴承信号为源域,以通轴轴承信号为目标域,以Inception-LSTM网络为基础,使用多核最大均值差异(Multi-kernel Maximum Mean Discrepancies,MKMMD)减小分布差异,实现故障样本不平衡条件下的跨转速域不变特征提取和迁移诊断。最后,利用实验数据和实测数据验证本算法的有效性,结果表明,该方法能有效诊断出退火窑辊道系统轴承故障,且具有较高的准确率。
