【摘要】 提出了一种基于BP神经网络的板带轧机液压HGC状态监测方法，利用BP神经网络算法进行模型训练和状态识别。通过对历史数据的分析和学习，建立了液压HGC状态与传感器数据之间的映射关系。然后，利用训练好的神经网络模型对实时数据进行监测和预测，从而实现对液压HGC系统状态的实时监测和故障预警。该方法能够准确监测液压HGC系统的状态，并提供及时的预警信息，为轧机运行维护和产品质量提升提供了有效的支持。更多还原

【Abstract】 This paper proposes a hydraulic HGC(Hydraulic Gap Control) state monitoring method for plate and strip rolling mills based on BP neural network. The BP neural network algorithm is utilized for model training and state recognition. By analyzing and learning from historical data, a mapping relationship between the hydraulic HGC state and sensor data is established. Subsequently, the trained neural network model is used to monitor and predict real-time data, enabling real-time monitoring and fault warning of the hydraulic HGC system. This method accurately monitors the state of the hydraulic HGC system and provides timely warning information, thereby providing effective support for operation, maintenance, and production quality improvement of the rolling mill.更多还原