论文部分内容阅读
相对于单一故障诊断,混合故障的特征分离历来是诊断领域的一大难题。针对某高线轧机的一次多故障并发的振动信号,引入了独立分量分析(ICA)技术,以负熵最大化为分离判据,以牛顿迭代法为优化算法,实现了滚动轴承故障特征的有效分离和提取,为设备安全运行提供理论依据。
The characteristic separation of hybrid faults has always been a big challenge in the field of diagnostics, relative to single fault diagnosis. Aiming at a multi-fault synchronous vibration signal of a high-speed rolling mill, independent component analysis (ICA) was introduced to maximize the negative entropy as the separation criterion. Newton’s iterative method was used as the optimization algorithm to realize the effective separation of the rolling bearing fault features And extraction, provide a theoretical basis for the safe operation of the equipment.