The paper probes into a probable condition that causes temper mill chatter from aspect of electromechanical coupling of complex electromechanical system, and mainly studies the effect of temper mill electrical driving...The paper probes into a probable condition that causes temper mill chatter from aspect of electromechanical coupling of complex electromechanical system, and mainly studies the effect of temper mill electrical driving system harmonic current on the main motion of temper mill set. Aiming at the electrical driving system of CM04 temper mill, the effect of harmonic current is analyzed and evaluated according to different load. Combining the features of CM04 temper mill′s structure and its working state, the paper discusses in every detail how the harmonic current in main circuit, which can be regarded as a disturbance via feedback control circuit , influences main motion of temper mill set.展开更多
平整机轧制力的预报对轧制过程的优化控制有着重要意义。针对平整机轧制力预测精度不高的问题,提出采用Re LU(Rectified Linear Units)激活函数的神经网络模型来预报平整机的轧制力。在对数据进行主成分分析后,得到影响轧制力的主要因素...平整机轧制力的预报对轧制过程的优化控制有着重要意义。针对平整机轧制力预测精度不高的问题,提出采用Re LU(Rectified Linear Units)激活函数的神经网络模型来预报平整机的轧制力。在对数据进行主成分分析后,得到影响轧制力的主要因素,并将其作为神经网络的输入层,将平整机轧制力作为输出层,通过使用Python语言编程进行实验,对神经网络模型隐层的相关参数及算法进行单一变量筛选,建立了保证轧制力预报精度最高的神经网络模型。实验结果表明,通过调整隐层层数、神经元数、传播算法、正则化方法,该模型能够将预测误差控制在10%以内,且该实验方法能够对不同输入参数下的平整机轧制力进行精确预报。展开更多
文摘The paper probes into a probable condition that causes temper mill chatter from aspect of electromechanical coupling of complex electromechanical system, and mainly studies the effect of temper mill electrical driving system harmonic current on the main motion of temper mill set. Aiming at the electrical driving system of CM04 temper mill, the effect of harmonic current is analyzed and evaluated according to different load. Combining the features of CM04 temper mill′s structure and its working state, the paper discusses in every detail how the harmonic current in main circuit, which can be regarded as a disturbance via feedback control circuit , influences main motion of temper mill set.
文摘平整机轧制力的预报对轧制过程的优化控制有着重要意义。针对平整机轧制力预测精度不高的问题,提出采用Re LU(Rectified Linear Units)激活函数的神经网络模型来预报平整机的轧制力。在对数据进行主成分分析后,得到影响轧制力的主要因素,并将其作为神经网络的输入层,将平整机轧制力作为输出层,通过使用Python语言编程进行实验,对神经网络模型隐层的相关参数及算法进行单一变量筛选,建立了保证轧制力预报精度最高的神经网络模型。实验结果表明,通过调整隐层层数、神经元数、传播算法、正则化方法,该模型能够将预测误差控制在10%以内,且该实验方法能够对不同输入参数下的平整机轧制力进行精确预报。
